mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-31 13:39:40 +00:00
Compare commits
42 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| ea5cabe6ff | |||
| 228ecd480f | |||
| e4152a2481 | |||
| 4c12ad427f | |||
| 6e196eea0e | |||
| 573e7d0243 | |||
| 4808d8457e | |||
| 6f2e71ec31 | |||
| 59a7d1b0a0 | |||
| 54a2fef9f0 | |||
| 0a4510c74e | |||
| 8e2a077f09 | |||
| 414d0eecbd | |||
| af4d15f9ac | |||
| 1f35876d16 | |||
| 570c58873f | |||
| bff56dda2c | |||
| fc90a56c52 | |||
| efdc920137 | |||
| f2d64506e3 | |||
| 63efc93b0c | |||
| 62600065cd | |||
| 0d0737ab57 | |||
| 1fe58f2d3a | |||
| bd2a796217 | |||
| 4c302572c0 | |||
| 72a1858015 | |||
| 2b578e68f6 | |||
| 7b1419a7fa | |||
| fbe8f5c9da | |||
| d632a103ae | |||
| 7e0fd0d653 | |||
| 0187856202 | |||
| 2939168c33 | |||
| 40a5e70352 | |||
| 0cef9cd197 | |||
| 643ffb4785 | |||
| d59505a735 | |||
| 6ac95363b0 | |||
| ede1fc2978 | |||
| 49d5ea49bc | |||
| d23b65416f |
@@ -72,19 +72,19 @@ jobs:
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -95,7 +95,7 @@ jobs:
|
||||
# from source-copy, so code-only changes skip the slow uv-sync layer
|
||||
# when the runner has a warm Docker daemon cache.
|
||||
- name: Build Libero benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.libero
|
||||
@@ -151,7 +151,7 @@ jobs:
|
||||
|
||||
- name: Upload Libero rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: libero-rollout-video
|
||||
path: /tmp/libero-artifacts/videos/
|
||||
@@ -159,7 +159,7 @@ jobs:
|
||||
|
||||
- name: Upload Libero eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: libero-metrics
|
||||
path: /tmp/libero-artifacts/metrics.json
|
||||
@@ -214,7 +214,7 @@ jobs:
|
||||
|
||||
- name: Upload Libero train-smoke eval video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: libero-train-smoke-video
|
||||
path: /tmp/libero-train-smoke-artifacts/eval/
|
||||
@@ -230,19 +230,19 @@ jobs:
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -250,7 +250,7 @@ jobs:
|
||||
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
|
||||
- name: Build MetaWorld benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.metaworld
|
||||
@@ -303,7 +303,7 @@ jobs:
|
||||
|
||||
- name: Upload MetaWorld rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: metaworld-rollout-video
|
||||
path: /tmp/metaworld-artifacts/videos/
|
||||
@@ -311,7 +311,7 @@ jobs:
|
||||
|
||||
- name: Upload MetaWorld eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: metaworld-metrics
|
||||
path: /tmp/metaworld-artifacts/metrics.json
|
||||
@@ -332,19 +332,19 @@ jobs:
|
||||
ROBOTWIN_TASKS: beat_block_hammer,click_bell,handover_block,stack_blocks_two,click_alarmclock,open_microwave,adjust_bottle,lift_pot,stamp_seal,turn_switch
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -355,7 +355,7 @@ jobs:
|
||||
# simulation assets (~4 GB). Layer cache lives in the runner's local
|
||||
# Docker daemon — reused across re-runs on the same machine.
|
||||
- name: Build RoboTwin 2.0 benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.robotwin
|
||||
@@ -413,7 +413,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboTwin rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
uses: actions/upload-artifact@v7
|
||||
with:
|
||||
name: robotwin-rollout-video
|
||||
path: /tmp/robotwin-artifacts/videos/
|
||||
@@ -421,7 +421,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboTwin eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
uses: actions/upload-artifact@v7
|
||||
with:
|
||||
name: robotwin-metrics
|
||||
path: /tmp/robotwin-artifacts/metrics.json
|
||||
@@ -439,19 +439,19 @@ jobs:
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -459,7 +459,7 @@ jobs:
|
||||
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
|
||||
- name: Build RoboCasa365 benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.robocasa
|
||||
@@ -514,7 +514,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboCasa365 rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: robocasa-rollout-video
|
||||
path: /tmp/robocasa-artifacts/videos/
|
||||
@@ -522,7 +522,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboCasa365 eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: robocasa-metrics
|
||||
path: /tmp/robocasa-artifacts/metrics.json
|
||||
@@ -540,19 +540,19 @@ jobs:
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -560,7 +560,7 @@ jobs:
|
||||
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
|
||||
- name: Build RoboCerebra benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.robocerebra
|
||||
@@ -621,7 +621,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboCerebra rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: robocerebra-rollout-video
|
||||
path: /tmp/robocerebra-artifacts/videos/
|
||||
@@ -629,7 +629,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboCerebra eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: robocerebra-metrics
|
||||
path: /tmp/robocerebra-artifacts/metrics.json
|
||||
@@ -648,19 +648,19 @@ jobs:
|
||||
ROBOMME_TASKS: PickXtimes,BinFill,StopCube,MoveCube,InsertPeg,SwingXtimes,VideoUnmask,ButtonUnmask,PickHighlight,PatternLock
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -668,7 +668,7 @@ jobs:
|
||||
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
|
||||
- name: Build RoboMME benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.robomme
|
||||
@@ -726,7 +726,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboMME rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: robomme-rollout-video
|
||||
path: /tmp/robomme-artifacts/videos/
|
||||
@@ -734,7 +734,7 @@ jobs:
|
||||
|
||||
- name: Upload RoboMME eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: robomme-metrics
|
||||
path: /tmp/robomme-artifacts/metrics.json
|
||||
@@ -754,19 +754,19 @@ jobs:
|
||||
LIBERO_PLUS_TASK_IDS: "[0,100,260,500,1000,1500,2000,2400]"
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -774,7 +774,7 @@ jobs:
|
||||
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
|
||||
- name: Build LIBERO-plus benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.libero_plus
|
||||
@@ -834,7 +834,7 @@ jobs:
|
||||
|
||||
- name: Upload LIBERO-plus rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: libero-plus-rollout-video
|
||||
path: /tmp/libero-plus-artifacts/videos/
|
||||
@@ -842,7 +842,7 @@ jobs:
|
||||
|
||||
- name: Upload LIBERO-plus eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: libero-plus-metrics
|
||||
path: /tmp/libero-plus-artifacts/metrics.json
|
||||
@@ -858,19 +858,19 @@ jobs:
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
|
||||
- name: Login to Docker Hub
|
||||
if: ${{ env.DOCKERHUB_USERNAME != '' }}
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
@@ -878,7 +878,7 @@ jobs:
|
||||
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
|
||||
- name: Build VLABench benchmark image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: docker/Dockerfile.benchmark.vlabench
|
||||
@@ -936,7 +936,7 @@ jobs:
|
||||
|
||||
- name: Upload VLABench rollout video
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: vlabench-rollout-video
|
||||
path: /tmp/vlabench-artifacts/videos/
|
||||
@@ -944,7 +944,7 @@ jobs:
|
||||
|
||||
- name: Upload VLABench eval metrics
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: vlabench-metrics
|
||||
path: /tmp/vlabench-artifacts/metrics.json
|
||||
|
||||
@@ -47,7 +47,7 @@ jobs:
|
||||
timeout-minutes: 30
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
|
||||
@@ -52,21 +52,21 @@ jobs:
|
||||
sudo apt-get update
|
||||
sudo apt-get install git-lfs
|
||||
git lfs install
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v7
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
- name: Login to Docker Hub
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
- name: Build and push Docker image CPU
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: ./docker/Dockerfile.user
|
||||
@@ -87,21 +87,21 @@ jobs:
|
||||
sudo apt-get update
|
||||
sudo apt-get install git-lfs
|
||||
git lfs install
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v7
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
- name: Login to Docker Hub
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
- name: Build and push Docker image GPU
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: ./docker/Dockerfile.internal
|
||||
|
||||
@@ -33,7 +33,7 @@ jobs:
|
||||
github.event.workflow_run.event == 'pull_request' &&
|
||||
github.event.workflow_run.conclusion == 'success' &&
|
||||
github.repository == 'huggingface/lerobot'
|
||||
uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@2430c1ec91d04667414e2fa31ecfc36c153ea391 # main
|
||||
uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@6108e850ae1cf2f71bb0815a600bcd50c39abfa7 # main
|
||||
with:
|
||||
package_name: lerobot
|
||||
secrets:
|
||||
|
||||
@@ -55,7 +55,7 @@ jobs:
|
||||
github.repository == 'huggingface/lerobot'
|
||||
permissions:
|
||||
contents: read
|
||||
uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@e60a538eea9817ab312196d0d233604b01697265 # main
|
||||
uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@6108e850ae1cf2f71bb0815a600bcd50c39abfa7 # main
|
||||
with:
|
||||
commit_sha: ${{ github.sha }}
|
||||
package: lerobot
|
||||
@@ -78,7 +78,7 @@ jobs:
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@e60a538eea9817ab312196d0d233604b01697265 # main
|
||||
uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@6108e850ae1cf2f71bb0815a600bcd50c39abfa7 # main
|
||||
with:
|
||||
commit_sha: ${{ github.event.pull_request.head.sha }}
|
||||
pr_number: ${{ github.event.number }}
|
||||
|
||||
@@ -69,7 +69,7 @@ jobs:
|
||||
HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
lfs: true
|
||||
@@ -87,7 +87,7 @@ jobs:
|
||||
libusb-1.0-0-dev speech-dispatcher libgeos-dev portaudio19-dev
|
||||
|
||||
- name: Setup uv and Python
|
||||
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
|
||||
uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
|
||||
with:
|
||||
enable-cache: true
|
||||
version: ${{ env.UV_VERSION }}
|
||||
|
||||
@@ -63,7 +63,7 @@ jobs:
|
||||
HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
@@ -80,7 +80,7 @@ jobs:
|
||||
speech-dispatcher libgeos-dev portaudio19-dev
|
||||
|
||||
- name: Setup uv and Python
|
||||
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
|
||||
uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
|
||||
with:
|
||||
enable-cache: true
|
||||
version: ${{ env.UV_VERSION }}
|
||||
@@ -137,21 +137,21 @@ jobs:
|
||||
sudo apt-get update
|
||||
sudo apt-get install git-lfs
|
||||
git lfs install
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
|
||||
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
|
||||
with:
|
||||
cache-binary: false
|
||||
- name: Login to Docker Hub
|
||||
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
|
||||
uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0 # v4.4.0
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
|
||||
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
|
||||
with:
|
||||
context: .
|
||||
file: ./docker/Dockerfile.internal
|
||||
|
||||
@@ -29,7 +29,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
if: github.repository == 'huggingface/lerobot'
|
||||
steps:
|
||||
- uses: actions/github-script@v8
|
||||
- uses: actions/github-script@v9
|
||||
with:
|
||||
script: |
|
||||
// Setup Input Text
|
||||
|
||||
@@ -48,12 +48,12 @@ jobs:
|
||||
outputs:
|
||||
changed: ${{ steps.diff.outputs.changed }}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v7
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Setup uv and Python
|
||||
uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: astral-sh/setup-uv@v8.3.2 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
version: ${{ env.UV_VERSION }}
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
@@ -74,7 +74,7 @@ jobs:
|
||||
|
||||
- name: Upload updated lockfile
|
||||
if: steps.diff.outputs.changed == 'true'
|
||||
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/upload-artifact@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: uv-lock
|
||||
path: uv.lock
|
||||
@@ -93,13 +93,13 @@ jobs:
|
||||
HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
|
||||
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v7
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
|
||||
- name: Download updated lockfile
|
||||
uses: actions/download-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/download-artifact@v8 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: uv-lock
|
||||
|
||||
@@ -115,7 +115,7 @@ jobs:
|
||||
speech-dispatcher libgeos-dev portaudio19-dev
|
||||
|
||||
- name: Setup uv and Python
|
||||
uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: astral-sh/setup-uv@v8.3.2 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
enable-cache: true
|
||||
version: ${{ env.UV_VERSION }}
|
||||
@@ -153,27 +153,27 @@ jobs:
|
||||
sudo apt-get update
|
||||
sudo apt-get install git-lfs
|
||||
git lfs install
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v7
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
|
||||
- name: Download updated lockfile
|
||||
uses: actions/download-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/download-artifact@v8 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: uv-lock
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/setup-buildx-action@v4 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
cache-binary: false
|
||||
- name: Login to Docker Hub
|
||||
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/login-action@v4.4.0 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
|
||||
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
|
||||
uses: docker/build-push-action@v7 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
context: .
|
||||
file: ./docker/Dockerfile.internal
|
||||
@@ -247,12 +247,12 @@ jobs:
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.UPDATE_LOCK_TOKEN }}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v7
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Download updated lockfile
|
||||
uses: actions/download-artifact@v4 # zizmor: ignore[unpinned-uses]
|
||||
uses: actions/download-artifact@v8 # zizmor: ignore[unpinned-uses]
|
||||
with:
|
||||
name: uv-lock
|
||||
|
||||
|
||||
@@ -33,7 +33,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
if: github.repository == 'huggingface/lerobot' && !github.event.pull_request.draft
|
||||
steps:
|
||||
- uses: actions/labeler@v6
|
||||
- uses: actions/labeler@v7
|
||||
with:
|
||||
repo-token: ${{ secrets.GITHUB_TOKEN }}
|
||||
sync-labels: true # Removes labels if files are removed from the PR
|
||||
|
||||
@@ -43,12 +43,12 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
|
||||
uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v6
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
|
||||
@@ -38,12 +38,12 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
|
||||
uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v6
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
@@ -104,7 +104,7 @@ jobs:
|
||||
- name: Publish to TestPyPI for pre-releases
|
||||
# True for tags like 'v0.2.0-rc1'
|
||||
if: startsWith(github.ref, 'refs/tags/v') && contains(github.ref, '-')
|
||||
uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0
|
||||
uses: pypa/gh-action-pypi-publish@ba38be9e461d3875417946c167d0b5f3d385a247 # v1.14.1
|
||||
with:
|
||||
repository-url: https://test.pypi.org/legacy/
|
||||
verbose: true
|
||||
@@ -112,7 +112,7 @@ jobs:
|
||||
|
||||
- name: Publish to PyPI
|
||||
if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
|
||||
uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0
|
||||
uses: pypa/gh-action-pypi-publish@ba38be9e461d3875417946c167d0b5f3d385a247 # v1.14.1
|
||||
with:
|
||||
verbose: true
|
||||
print-hash: true
|
||||
@@ -127,7 +127,7 @@ jobs:
|
||||
env:
|
||||
MUJOCO_GL: egl
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
lfs: true
|
||||
persist-credentials: false
|
||||
@@ -137,7 +137,7 @@ jobs:
|
||||
git curl libglib2.0-0 libegl1-mesa-dev ffmpeg libusb-1.0-0-dev \
|
||||
speech-dispatcher libgeos-dev portaudio19-dev
|
||||
- name: Setup uv and Python
|
||||
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
|
||||
uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
|
||||
with:
|
||||
enable-cache: true # zizmor: ignore[cache-poisoning]
|
||||
version: ${{ env.UV_VERSION }}
|
||||
|
||||
@@ -43,12 +43,12 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
fetch-depth: 0
|
||||
persist-credentials: false
|
||||
|
||||
- name: Secret Scanning
|
||||
uses: trufflesecurity/trufflehog@eafb8c5f6a06175141c27f17bcc17941853d0047 # v3.90.0
|
||||
uses: trufflesecurity/trufflehog@27b0417c16317ca9a472a9a8092acce143b49c55 # v3.95.9
|
||||
with:
|
||||
extra_args: --only-verified
|
||||
|
||||
@@ -65,7 +65,7 @@ In summary, you need to specify instructions for:
|
||||
Importantly,
|
||||
|
||||
- `actions_per_chunk` and `chunk_size_threshold` are key parameters to tune for your setup.
|
||||
- `aggregate_fn_name` is the function to aggregate actions on overlapping portions. You can either add a new one to a registry of functions, or add your own in `robot_client.py` (see [here](NOTE:addlinktoLOC))
|
||||
- `aggregate_fn_name` is the function to aggregate actions on overlapping portions. You can either add a new one to a registry of functions, or add your own in `robot_client.py` (see [here](https://github.com/huggingface/lerobot/blob/main/src/lerobot/async_inference/robot_client.py#L224))
|
||||
- `debug_visualize_queue_size` is a useful tool to tune the `CLIENT` parameters.
|
||||
|
||||
## Done! You should see your robot moving around by now 😉
|
||||
|
||||
@@ -164,8 +164,8 @@ includes the range reported by the sensor. Requesting an unsupported control als
|
||||
Omitted controls leave the sensor's existing automatic or manual setting unchanged. These options
|
||||
require `use_rgb=True`.
|
||||
|
||||
On the RealSense D405, the color stream is provided by the Stereo Module, so changing manual
|
||||
exposure or gain also affects the depth stream.
|
||||
Manual color controls require a dedicated RGB module. Cameras without one, such as the RealSense
|
||||
D405, do not support them and raise an error at connection time.
|
||||
|
||||
</hfoption>
|
||||
</hfoptions>
|
||||
|
||||
@@ -59,6 +59,7 @@ The `lerobot-rollout --strategy.type=dagger` mode requires **teleoperators with
|
||||
|
||||
- `bi_openarm_mini` - Bimanual OpenArm Mini
|
||||
- `so_leader` - SO100 / SO101 leader arm
|
||||
- `bi_so_leader` - Bimanual SO100 / SO101 leader arms
|
||||
|
||||
> [!IMPORTANT]
|
||||
> The provided commands default to `bi_openarm_follower` + `bi_openarm_mini`.
|
||||
|
||||
@@ -98,7 +98,7 @@ The teleoperate command will automatically:
|
||||
|
||||
## Cameras
|
||||
|
||||
To add cameras to your setup, follow this [Guide](./cameras#setup-cameras).
|
||||
To add cameras to your setup, follow this [Guide](./cameras).
|
||||
|
||||
## Teleoperate with cameras
|
||||
|
||||
|
||||
+163
-9
@@ -1,23 +1,177 @@
|
||||
# LeRobot
|
||||
|
||||
<div class="flex justify-center">
|
||||
<a target="_blank" href="https://huggingface.co/lerobot">
|
||||
<img
|
||||
alt="HuggingFace Expert Acceleration Program"
|
||||
alt="LeRobot, Hugging Face Robotics Library"
|
||||
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/lerobot/lerobot-logo-thumbnail.png"
|
||||
style="width: 100%"
|
||||
></img>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
# LeRobot
|
||||
|
||||
**State-of-the-art machine learning for real-world robotics**
|
||||
|
||||
🤗 LeRobot aims to provide models, datasets, and tools for real-world robotics in PyTorch. The goal is to lower the barrier for entry to robotics so that everyone can contribute and benefit from sharing datasets and pretrained models.
|
||||
🤗 LeRobot provides a hardware-agnostic, Python-native interface for controlling real robots - from affordable arms like the SO-ARM101 to full humanoids. Plus the tools to record, store, and share the datasets they generate. Every dataset uses the standardized **LeRobotDataset** format (synchronized video + action/state data) and can be streamed directly from the [Hugging Face Hub](https://huggingface.co/lerobot).
|
||||
|
||||
🤗 LeRobot contains state-of-the-art approaches that have been shown to transfer to the real-world with a focus on imitation learning and reinforcement learning.
|
||||
🤗 On top of that data, LeRobot implements state-of-the-art policies - from lightweight imitation-learning models like ACT to large vision-language-action models like π₀ and SmolVLA - all trainable, shareable, and deployable with the same handful of CLI commands.
|
||||
|
||||
🤗 LeRobot already provides a set of pretrained models, datasets with human collected demonstrations, and simulated environments so that everyone can get started.
|
||||
The goal: lower the barrier to entry for robotics, so that everyone can contribute to, and benefit from, shared datasets and pretrained models.
|
||||
|
||||
🤗 LeRobot hosts pretrained models and datasets on the LeRobot HuggingFace page.
|
||||
<div align="center" style="display: flex; justify-content: center; gap: 8px; flex-wrap: wrap; margin: 20px 0;">
|
||||
<a href="https://discord.gg/s3KuuzsPFb" target="_blank">
|
||||
<img alt="Discord" src="https://img.shields.io/badge/Discord-Join_the_Community-5865F2?style=flat&logo=discord&logoColor=white">
|
||||
</a>
|
||||
<a href="https://x.com/LeRobotHF" target="_blank">
|
||||
<img alt="X (Twitter)" src="https://img.shields.io/badge/X-Follow_%40LeRobotHF-black?style=flat&logo=x&logoColor=white">
|
||||
</a>
|
||||
<a href="https://huggingface.co/lerobot" target="_blank">
|
||||
<img alt="Hugging Face Hub" src="https://img.shields.io/badge/HF_Hub-Models_%26_Datasets-FFD21E?style=flat">
|
||||
</a>
|
||||
</div>
|
||||
|
||||
Join the LeRobot community on [Discord](https://discord.gg/s3KuuzsPFb)
|
||||
<div align="center">
|
||||
<img src="../../media/readme/robots_control_video.webp" width="640px" alt="Reachy 2 Demo">
|
||||
</div>
|
||||
|
||||
## How It Works
|
||||
|
||||
**Teleoperate → Record → Train → Deploy**
|
||||
|
||||
1. **Teleoperate** - control the robot yourself (with a leader arm, keyboard, or phone) so it can learn from your movements.
|
||||
2. **Record** - each demonstration is saved as a dataset: synchronized camera video plus the actions you took.
|
||||
3. **Train** - a policy (the neural network that will control the robot) learns to imitate your demonstrations.
|
||||
4. **Deploy** - run the trained policy on the robot and watch it complete the task on its own.
|
||||
|
||||
## Get Started
|
||||
|
||||
New here? [Install LeRobot](./installation), then pick your path:
|
||||
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-4 my-6">
|
||||
<div class="border dark:border-gray-700 rounded-lg p-4 shadow">
|
||||
<div class="text-lg font-semibold mb-2">🔧 I have a robot</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
LeRobot supports a wide range of arms and mobile robots. Popular picks:
|
||||
</p>
|
||||
<ul class="text-gray-700 dark:text-gray-300 text-sm list-disc pl-5 mb-2">
|
||||
<li>
|
||||
<a href="./so101">SO-101</a> - our flagship, low-cost arm
|
||||
</li>
|
||||
<li>
|
||||
<a href="./lekiwi">LeKiwi</a> - a mobile base with an arm on top
|
||||
</li>
|
||||
<li>
|
||||
<a href="./koch">Koch v1.1</a> - a long-time community favorite
|
||||
</li>
|
||||
<li>
|
||||
or find yours under <strong>Robots</strong> in the sidebar
|
||||
</li>
|
||||
</ul>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Once it's assembled and calibrated, record a dataset and train your first
|
||||
policy with the <a href="./il_robots">imitation learning tutorial</a> - or
|
||||
skip the CLI entirely with <a href="./lelab">LeLab</a>, a browser GUI for
|
||||
the same workflow.
|
||||
</p>
|
||||
</div>
|
||||
<div class="border dark:border-gray-700 rounded-lg p-4 shadow">
|
||||
<div class="text-lg font-semibold mb-2">💻 No hardware yet</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
You can still train and evaluate policies without owning a robot:
|
||||
</p>
|
||||
<ul class="text-gray-700 dark:text-gray-300 text-sm list-disc pl-5 mb-2">
|
||||
<li>
|
||||
train on an existing
|
||||
<a href="https://huggingface.co/datasets?other=LeRobot">
|
||||
LeRobot dataset
|
||||
</a>
|
||||
from the Hub
|
||||
</li>
|
||||
<li>
|
||||
evaluate in <a href="./envhub">simulation</a>, against benchmarks like
|
||||
LIBERO or Meta-World
|
||||
</li>
|
||||
<li>
|
||||
try the free <a href="./notebooks">Colab notebooks</a> - nothing to
|
||||
install
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="border dark:border-gray-700 rounded-lg p-4 shadow">
|
||||
<div class="text-lg font-semibold mb-2">🤝 I want to contribute</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Start with the <a href="./contributing">Contributing guide</a>, then
|
||||
<a href="./bring_your_own_policies">add a new policy</a> or
|
||||
<a href="./integrate_hardware">bring your own hardware</a>.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
## Explore the Docs
|
||||
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-4 my-6">
|
||||
<a
|
||||
class="!no-underline border dark:border-gray-700 rounded-lg p-4 shadow hover:shadow-lg"
|
||||
href="./cheat-sheet"
|
||||
>
|
||||
<div class="font-semibold mb-1">📋 Cheat Sheet</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Every LeRobot CLI command, copy-paste ready.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
class="!no-underline border dark:border-gray-700 rounded-lg p-4 shadow hover:shadow-lg"
|
||||
href="./hardware_guide"
|
||||
>
|
||||
<div class="font-semibold mb-1">🖥️ Compute & Hardware Guide</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Which policy fits your GPU, and how long training takes.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
class="!no-underline border dark:border-gray-700 rounded-lg p-4 shadow hover:shadow-lg"
|
||||
href="./lerobot-dataset-v3"
|
||||
>
|
||||
<div class="font-semibold mb-1">🗂️ LeRobotDataset</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Load, stream, and visualize robot datasets from the Hub.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
class="!no-underline border dark:border-gray-700 rounded-lg p-4 shadow hover:shadow-lg"
|
||||
href="./lelab"
|
||||
>
|
||||
<div class="font-semibold mb-1">🖼 LeLab</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
A browser GUI for calibrating, recording, and training - no CLI required.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
class="!no-underline border dark:border-gray-700 rounded-lg p-4 shadow hover:shadow-lg"
|
||||
href="./act"
|
||||
>
|
||||
<div class="font-semibold mb-1">🧠 Policies</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Start with ACT, our recommended first policy - or browse SmolVLA, π₀, and
|
||||
more in the sidebar.
|
||||
</p>
|
||||
</a>
|
||||
<a
|
||||
class="!no-underline border dark:border-gray-700 rounded-lg p-4 shadow hover:shadow-lg"
|
||||
href="./envhub"
|
||||
>
|
||||
<div class="font-semibold mb-1">🎮 Simulation & Benchmarks</div>
|
||||
<p class="text-gray-700 dark:text-gray-300 text-sm">
|
||||
Train and evaluate in simulated environments before touching real
|
||||
hardware.
|
||||
</p>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
## Common Problems
|
||||
|
||||
Running into issues? A few of the most frequent ones:
|
||||
|
||||
- **Blurry or unusable camera footage** - lighting matters more than resolution. See the [Cameras](./cameras) guide.
|
||||
- **Build or install errors** (`cmake`, `ffmpeg`, CUDA) - see the Troubleshooting section of the [Installation guide](./installation#troubleshooting).
|
||||
- **Not sure which policy fits your GPU** - check the [Compute & Hardware Guide](./hardware_guide).
|
||||
- **Still stuck?** Ask on [Discord](https://discord.gg/s3KuuzsPFb) - the community (and the LeRobot team) is there to help.
|
||||
|
||||
+17
-15
@@ -149,13 +149,14 @@ lerobot-rollout \
|
||||
|
||||
Foot pedal input is also supported via `--strategy.input_device=pedal`. Configure pedal codes with `--strategy.pedal.*` flags.
|
||||
|
||||
| Flag | Description |
|
||||
| ------------------------------------ | ------------------------------------------------------- |
|
||||
| `--strategy.num_episodes` | Number of correction episodes to record (default: 10) |
|
||||
| `--strategy.record_autonomous` | Record autonomous frames too (default: false) |
|
||||
| `--strategy.upload_every_n_episodes` | Push to Hub every N episodes (default: 5) |
|
||||
| `--strategy.input_device` | Input device: `keyboard` or `pedal` (default: keyboard) |
|
||||
| `--teleop.type` | **Required.** Teleoperator type |
|
||||
| Flag | Description |
|
||||
| ------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--strategy.num_episodes` | Number of correction episodes to record (default: 10) |
|
||||
| `--strategy.record_autonomous` | Record autonomous frames too (default: false) |
|
||||
| `--strategy.upload_every_n_episodes` | Push to Hub every N episodes (default: 5) |
|
||||
| `--strategy.input_device` | Input device: `keyboard` or `pedal` (default: keyboard) |
|
||||
| `--strategy.smooth_handover` | Smoothly hand control over at pause / correction start (default: true). Disable for clutch-style teleops that re-reference at the current robot pose on engage |
|
||||
| `--teleop.type` | **Required.** Teleoperator type |
|
||||
|
||||
### Episodic (`--strategy.type=episodic`)
|
||||
|
||||
@@ -186,14 +187,15 @@ Teleop is optional — if omitted the robot holds its position during the reset
|
||||
| `←` (left) | Discard episode and re-record it |
|
||||
| `ESC` | Stop the recording session |
|
||||
|
||||
| Flag | Description |
|
||||
| ----------------------------------------------- | -------------------------------------------------------------------------- |
|
||||
| `--dataset.num_episodes` | Number of episodes to record |
|
||||
| `--dataset.episode_time_s` | Duration of each recording episode in seconds |
|
||||
| `--dataset.reset_time_s` | Duration of the reset phase between episodes in seconds |
|
||||
| `--teleop.type` | Optional. Teleoperator to drive the robot during resets |
|
||||
| `--strategy.reset_to_initial_position` | Whether to reset the robot to its initial position between episodes |
|
||||
| `--strategy.smooth_leader_to_follower_handover` | Whether to turn on or off the leader -> follower smooth handover behavior. |
|
||||
| Flag | Description |
|
||||
| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--dataset.num_episodes` | Number of episodes to record |
|
||||
| `--dataset.episode_time_s` | Duration of each recording episode in seconds |
|
||||
| `--dataset.reset_time_s` | Duration of the reset phase between episodes in seconds |
|
||||
| `--teleop.type` | Optional. Teleoperator to drive the robot during resets |
|
||||
| `--strategy.reset_to_initial_position` | Whether to reset the robot to its initial position between episodes |
|
||||
| `--strategy.smooth_leader_to_follower_handover` | Whether to turn on or off the leader -> follower smooth handover behavior. |
|
||||
| `--strategy.smooth_handover` | Smoothly hand control to the teleop at reset start (default: true). Disable for clutch-style teleops that re-reference at the current robot pose on engage |
|
||||
|
||||
---
|
||||
|
||||
|
||||
+32
-12
@@ -114,38 +114,58 @@ LIBERO supports two control modes — `relative` (default) and `absolute`. Diffe
|
||||
|
||||
### Recommended evaluation episodes
|
||||
|
||||
For reproducible benchmarking, use **10 episodes per task** across all four standard suites (Spatial, Object, Goal, Long). This gives 400 total episodes and matches the protocol used for published results.
|
||||
For reproducible benchmarking, use **10 episodes per task** across all four standard suites (Spatial, Object, Goal, Long). This gives 400 total episodes and matches the protocol used for published results. Success rates may vary by a few percent across evaluation seeds, so we recommend averaging over 3 seeds.
|
||||
|
||||
<Tip>
|
||||
To compare two policies on the same episodes, use the same `--seed`, keep
|
||||
`--env.init_states=true`, and run each task in a single batch
|
||||
(`--eval.batch_size` equal to episodes per task).
|
||||
</Tip>
|
||||
|
||||
## Training
|
||||
|
||||
### Dataset
|
||||
|
||||
We provide a preprocessed LIBERO dataset fully compatible with LeRobot:
|
||||
Two preprocessed LIBERO datasets are fully compatible with LeRobot. They contain the same demonstrations with the same schema and differ in how camera frames are stored:
|
||||
|
||||
- [HuggingFaceVLA/libero](https://huggingface.co/datasets/HuggingFaceVLA/libero)
|
||||
| | [lerobot/libero](https://huggingface.co/datasets/lerobot/libero) | [HuggingFaceVLA/libero](https://huggingface.co/datasets/HuggingFaceVLA/libero) |
|
||||
| ------------------------- | ---------------------------------------------------------------- | ------------------------------------------------------------------------------ |
|
||||
| episodes / frames / tasks | 1,693 / 273,465 / 40 | 1,693 / 273,465 / 40 |
|
||||
| cameras | 2× 256×256×3 | 2× 256×256×3 |
|
||||
| state / action dims | 8 / 7 | 8 / 7 |
|
||||
| dataset format | v3.0 | v3.0 |
|
||||
| camera encoding | MP4 video | PNG in parquet |
|
||||
| download size | **1.9 GB** | 69.9 GB |
|
||||
| extra dependency | video backend (`torchcodec` or `pyav`) | none |
|
||||
|
||||
**We recommend [lerobot/libero](https://huggingface.co/datasets/lerobot/libero)**: **37× smaller download** with **equivalent loading speed** (~330 samples/s per worker). Video re-encoding is slightly lossy; use the image-based variant if you cannot install a video decoding backend.
|
||||
|
||||
For reference, the original dataset published by Physical Intelligence:
|
||||
|
||||
- [physical-intelligence/libero](https://huggingface.co/datasets/physical-intelligence/libero)
|
||||
|
||||
<Tip>
|
||||
Pin `--dataset.revision=<commit-sha>` when reporting results — Hub datasets can be re-uploaded, and success rates are only comparable against the same data revision.
|
||||
</Tip>
|
||||
|
||||
### Example training command
|
||||
|
||||
Train SmolVLA on the recommended dataset:
|
||||
|
||||
```bash
|
||||
lerobot-train \
|
||||
--policy.type=smolvla \
|
||||
--policy.repo_id=${HF_USER}/libero-test \
|
||||
--policy.load_vlm_weights=true \
|
||||
--dataset.repo_id=HuggingFaceVLA/libero \
|
||||
--env.type=libero \
|
||||
--env.task=libero_10 \
|
||||
--output_dir=./outputs/ \
|
||||
--policy.push_to_hub=false \
|
||||
--dataset.repo_id=lerobot/libero \
|
||||
--dataset.video_backend=torchcodec \
|
||||
--output_dir=./outputs/libero_smolvla \
|
||||
--steps=100000 \
|
||||
--batch_size=4 \
|
||||
--eval.batch_size=1 \
|
||||
--eval.n_episodes=1 \
|
||||
--env_eval_freq=1000
|
||||
--batch_size=64
|
||||
```
|
||||
|
||||
To share the result on the Hub, replace `--policy.push_to_hub=false` with `--policy.repo_id=${HF_USER}/libero-smolvla`. Evaluate saved checkpoints with `lerobot-eval` as shown in the [Evaluation](#evaluation) section.
|
||||
|
||||
## Reproducing published results
|
||||
|
||||
We reproduce the results of Pi0.5 on the LIBERO benchmark. We take the Physical Intelligence LIBERO base model (`pi05_libero`) and finetune for an additional 6k steps in bfloat16, with batch size of 256 on 8 H100 GPUs using the [HuggingFace LIBERO dataset](https://huggingface.co/datasets/HuggingFaceVLA/libero).
|
||||
|
||||
+114
-24
@@ -36,6 +36,12 @@ This diverse training mixture creates a "curriculum" that enables generalization
|
||||
pip install -e ".[pi]"
|
||||
```
|
||||
|
||||
If you installed LeRobot from PyPI:
|
||||
|
||||
```bash
|
||||
pip install 'lerobot[pi]'
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
To use π₀.₅ in your LeRobot configuration, specify the policy type as:
|
||||
@@ -46,27 +52,106 @@ policy.type=pi05
|
||||
|
||||
## Training
|
||||
|
||||
### Training Command Example
|
||||
### Quickstart on LIBERO
|
||||
|
||||
Here's a complete training command for finetuning the base π₀.₅ model on your own dataset:
|
||||
Finetune the LIBERO base model on [lerobot/libero](https://huggingface.co/datasets/lerobot/libero), a ~1.9 GB video-encoded copy of the demonstrations behind the [results below](#libero-benchmark-results).
|
||||
|
||||
It carries the keys π₀.₅ reads, which are also the ones the LIBERO environment produces at evaluation time:
|
||||
|
||||
| Feature | Shape in the dataset | How π₀.₅ consumes it |
|
||||
| --------------------------- | -------------------- | ------------------------------------------------------- |
|
||||
| `observation.images.image` | 256×256×3, agentview | resized to 224×224 |
|
||||
| `observation.images.image2` | 256×256×3, wrist | resized to 224×224 |
|
||||
| `observation.state` | 8 | discretized into 256 bins and written into the prompt |
|
||||
| `action` | 7 | padded to 32 internally; the loss uses the first 7 dims |
|
||||
|
||||
**No `--rename_map` is needed here** — the keys already match; see [Rename Map and Empty Cameras](./rename_map) if yours differ.
|
||||
|
||||
<Tip>
|
||||
π₀.₅ uses the gated
|
||||
[google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224)
|
||||
tokenizer — accept its license on the Hub and log in with `hf auth login`
|
||||
before training.
|
||||
</Tip>
|
||||
|
||||
Sized for a single 80 GB GPU:
|
||||
|
||||
```bash
|
||||
lerobot-train \
|
||||
--dataset.repo_id=your_dataset \
|
||||
--dataset.repo_id=lerobot/libero \
|
||||
--policy.type=pi05 \
|
||||
--output_dir=./outputs/pi05_training \
|
||||
--job_name=pi05_training \
|
||||
--policy.repo_id=your_repo_id \
|
||||
--policy.pretrained_path=lerobot/pi05_base \
|
||||
--policy.compile_model=true \
|
||||
--policy.gradient_checkpointing=true \
|
||||
--wandb.enable=true \
|
||||
--policy.dtype=bfloat16 \
|
||||
--policy.pretrained_path=lerobot/pi05_libero_base \
|
||||
--policy.normalization_mapping='{"ACTION": "MEAN_STD", "STATE": "MEAN_STD", "VISUAL": "IDENTITY"}' \
|
||||
--policy.n_action_steps=10 \
|
||||
--policy.empty_cameras=1 \
|
||||
--policy.freeze_vision_encoder=false \
|
||||
--policy.train_expert_only=false \
|
||||
--steps=3000 \
|
||||
--policy.gradient_checkpointing=true \
|
||||
--policy.dtype=bfloat16 \
|
||||
--policy.device=cuda \
|
||||
--batch_size=32
|
||||
--policy.push_to_hub=false \
|
||||
--output_dir=./outputs/pi05_libero \
|
||||
--job_name=pi05_libero \
|
||||
--batch_size=64 \
|
||||
--num_workers=8 \
|
||||
--steps=30000 \
|
||||
--save_freq=5000 \
|
||||
--seed=1000
|
||||
```
|
||||
|
||||
**Mean/std normalization, not π₀.₅'s [quantile default](#quantile-statistics)** — matching [pi05_libero_finetuned_v044](https://huggingface.co/lerobot/pi05_libero_finetuned_v044), the checkpoint the results below were measured on.
|
||||
|
||||
**`--policy.n_action_steps=10` and `--policy.empty_cameras=1` are explicit** because `--policy.pretrained_path` loads weights only — `lerobot/pi05_libero_base` stores both, and they would otherwise fall back to `50` and `0` (see [Loading a checkpoint](#loading-a-checkpoint)).
|
||||
|
||||
Then evaluate a checkpoint with `lerobot-eval` and compare against the reference success rates — see [LIBERO](./libero).
|
||||
|
||||
### Quantile statistics
|
||||
|
||||
π₀.₅ normalizes `STATE` and `ACTION` with quantiles, so your dataset's `meta/stats.json` needs `q01` and `q99`. Older datasets carry only `min`/`max`/`mean`/`std` and fail on the first batch:
|
||||
|
||||
```
|
||||
ValueError: QUANTILES normalization mode requires q01 and q99 stats
|
||||
```
|
||||
|
||||
Recompute them:
|
||||
|
||||
```bash
|
||||
lerobot-edit-dataset \
|
||||
--repo_id your_dataset \
|
||||
--new_repo_id your_dataset \
|
||||
--operation.type recompute_stats \
|
||||
--operation.overwrite true
|
||||
```
|
||||
|
||||
**The result lands in `$HF_LEROBOT_HOME/your_dataset`**, not the cache `--dataset.repo_id` reads — so train with `--dataset.root=$HF_LEROBOT_HOME/your_dataset`, or add `--push_to_hub true` above.
|
||||
|
||||
Or keep the dataset as-is and pass `--policy.normalization_mapping='{"ACTION": "MEAN_STD", "STATE": "MEAN_STD", "VISUAL": "IDENTITY"}'`.
|
||||
|
||||
### Training Command Example
|
||||
|
||||
The same finetune with the VLM frozen: less memory, at some cost in success rate. Swap `--dataset.repo_id` for your own dataset.
|
||||
|
||||
```bash
|
||||
lerobot-train \
|
||||
--dataset.repo_id=lerobot/libero \
|
||||
--policy.type=pi05 \
|
||||
--policy.pretrained_path=lerobot/pi05_libero_base \
|
||||
--policy.normalization_mapping='{"ACTION": "MEAN_STD", "STATE": "MEAN_STD", "VISUAL": "IDENTITY"}' \
|
||||
--policy.n_action_steps=10 \
|
||||
--policy.empty_cameras=1 \
|
||||
--policy.freeze_vision_encoder=true \
|
||||
--policy.train_expert_only=true \
|
||||
--policy.gradient_checkpointing=true \
|
||||
--policy.dtype=bfloat16 \
|
||||
--policy.device=cuda \
|
||||
--policy.push_to_hub=false \
|
||||
--output_dir=./outputs/pi05_libero_expert \
|
||||
--job_name=pi05_libero_expert \
|
||||
--batch_size=64 \
|
||||
--num_workers=8 \
|
||||
--steps=30000 \
|
||||
--save_freq=5000 \
|
||||
--seed=1000
|
||||
```
|
||||
|
||||
### Key Training Parameters
|
||||
@@ -74,10 +159,24 @@ lerobot-train \
|
||||
- **`--policy.compile_model=true`**: Enables model compilation for faster training
|
||||
- **`--policy.gradient_checkpointing=true`**: Reduces memory usage significantly during training
|
||||
- **`--policy.dtype=bfloat16`**: Use mixed precision training for efficiency
|
||||
- **`--batch_size=32`**: Batch size for training, adapt this based on your GPU memory
|
||||
- **`--batch_size=64`**: Batch size for training, adapt this based on your GPU memory
|
||||
- **`--policy.pretrained_path=lerobot/pi05_base`**: The base π₀.₅ model you want to finetune, options are:
|
||||
- [lerobot/pi05_base](https://huggingface.co/lerobot/pi05_base)
|
||||
- [lerobot/pi05_libero](https://huggingface.co/lerobot/pi05_libero) (specifically trained on the Libero dataset)
|
||||
- [lerobot/pi05_libero_base](https://huggingface.co/lerobot/pi05_libero_base) (specifically trained on the Libero dataset)
|
||||
|
||||
### Loading a checkpoint
|
||||
|
||||
The two forms are not interchangeable:
|
||||
|
||||
| | `--policy.path` | `--policy.pretrained_path` |
|
||||
| -------------------------------------- | ---------------------------------------------- | ------------------------------------ |
|
||||
| Loads | weights **and** the checkpoint's `config.json` | weights only |
|
||||
| Feature names | from the checkpoint | from your dataset |
|
||||
| Stored settings, e.g. `n_action_steps` | inherited | reset to the defaults |
|
||||
| `--policy.type` | must be omitted | required |
|
||||
| `--rename_map` | needed when your camera keys differ | never — the keys come from your data |
|
||||
|
||||
Passing a `--rename_map` alongside `--policy.pretrained_path` renames the batch away from those names, and the first batch fails with `All image features are missing from the batch`.
|
||||
|
||||
### Training Parameters Explained
|
||||
|
||||
@@ -88,15 +187,6 @@ lerobot-train \
|
||||
|
||||
**💡 Tip**: Setting `train_expert_only=true` freezes the VLM and trains only the action expert and projections, allowing finetuning with reduced memory usage.
|
||||
|
||||
If your dataset is not converted with `quantiles`, you can convert it with the following command:
|
||||
|
||||
```bash
|
||||
python src/lerobot/scripts/augment_dataset_quantile_stats.py \
|
||||
--repo-id=your_dataset \
|
||||
```
|
||||
|
||||
Or train pi05 with this normalization mapping: `--policy.normalization_mapping='{"ACTION": "MEAN_STD", "STATE": "MEAN_STD", "VISUAL": "IDENTITY"}'`
|
||||
|
||||
## Relative Actions
|
||||
|
||||
By default, π₀.₅ predicts absolute actions. You can enable **relative actions** so the model predicts offsets relative to the current robot state. This can improve training stability for certain setups.
|
||||
|
||||
@@ -82,6 +82,8 @@ By default the env samples objects only from the `lightwheel` registry (what `--
|
||||
|
||||
All eval snippets below mirror the CI command (see `.github/workflows/benchmark_tests.yml`). The `--rename_map` argument maps RoboCasa's native camera keys (`robot0_agentview_left` / `robot0_eye_in_hand` / `robot0_agentview_right`) onto the three-camera (`camera1` / `camera2` / `camera3`) input layout the released `smolvla_robocasa` policy was trained on.
|
||||
|
||||
By default, each task uses the rollout horizon registered by RoboCasa. Set `--env.episode_length=<steps>` to apply the same explicit horizon to every selected task.
|
||||
|
||||
### Single-task evaluation (recommended for quick iteration)
|
||||
|
||||
```bash
|
||||
|
||||
@@ -35,14 +35,11 @@ pip install --override <(printf 'gymnasium==0.29.1\nnumpy==1.26.4\n') \
|
||||
### Docker (recommended)
|
||||
|
||||
```bash
|
||||
# Build base image first (from repo root)
|
||||
docker build -f docker/Dockerfile.eval-base -t lerobot-eval-base .
|
||||
|
||||
# Build RoboMME eval image (applies gymnasium + numpy pin overrides)
|
||||
docker build -f docker/Dockerfile.benchmark.robomme -t lerobot-robomme .
|
||||
# Build the RoboMME evaluation image from the repo root
|
||||
docker build -f docker/Dockerfile.benchmark.robomme -t lerobot-benchmark-robomme .
|
||||
```
|
||||
|
||||
The `docker/Dockerfile.benchmark.robomme` image overrides `gymnasium==0.29.1` and `numpy==1.26.4` after lerobot's install. Both versions are runtime-safe for lerobot's actual API usage.
|
||||
The benchmark Dockerfile extends the published `huggingface/lerobot-gpu:latest` image, then overrides `gymnasium==0.29.1` and `numpy==1.26.4`. Both versions are runtime-safe for lerobot's actual API usage.
|
||||
|
||||
## Running Evaluation
|
||||
|
||||
|
||||
@@ -338,7 +338,7 @@ It is advisable to install one 3-pin cable in the motor after placing them befor
|
||||
<hfoption id="Leader">
|
||||
|
||||
- Mount the leader holder onto the wrist and secure it with 4 M3x6mm screws.
|
||||
- Attach the handle to motor 5 using 1 M2x6mm screw.
|
||||
- Attach the handle to the leader holder using 1 M2x6mm screw.
|
||||
- Insert the gripper motor, secure it with 2 M2x6mm screws on each side, attach a motor horn using a M3x6mm horn screw.
|
||||
- Attach the follower trigger with 4 M3x6mm screws.
|
||||
|
||||
|
||||
@@ -290,47 +290,6 @@ lerobot-rollout \
|
||||
|
||||
---
|
||||
|
||||
## Part 5: SONIC Whole-Body Control (Latent-Token Policies)
|
||||
|
||||
LeRobot now ports the **decoder** half of NVIDIA's [SONIC](https://github.com/NVIDIA/sonic) whole-body deploy stack as the `SonicWholeBodyController`. Instead of commanding joints, the policy outputs a 64-D **latent motion token** (`motion_token.{i}.pos`) each tick; the SONIC decoder maps that token plus recent proprioception history onto a residual action that is scaled and added to the standing pose, producing 50 Hz joint-position targets for all 29 DoF.
|
||||
|
||||
The controller loads its ONNX decoder and all deploy constants (PD gains, `default_angles`, `action_scale`, and the neutral token) from [`lerobot/sonic_decoder`](https://huggingface.co/lerobot/sonic_decoder). The repo also ships a distilled low-latency decoder, selectable with the controller's `policy_type="low_latency"` argument (defaults to `"default"`).
|
||||
|
||||
### Test in Simulation
|
||||
|
||||
Any token-output policy trained on SONIC motion tokens (e.g. [`nepyope/sonic_walk`](https://huggingface.co/nepyope/sonic_walk)) can drive it:
|
||||
|
||||
```bash
|
||||
lerobot-rollout \
|
||||
--strategy.type=base \
|
||||
--policy.path=nepyope/sonic_walk \
|
||||
--policy.device=cuda \
|
||||
--robot.type=unitree_g1 \
|
||||
--robot.is_simulation=true \
|
||||
--robot.controller=SonicWholeBodyController \
|
||||
--robot.cameras='{"ego_view": {"type": "zmq", "server_address": "localhost", "port": 5555, "camera_name": "head_camera", "width": 640, "height": 480, "fps": 30, "warmup_s": 15}}'
|
||||
```
|
||||
|
||||
### Run on the Physical Robot
|
||||
|
||||
Start the robot server (see Part 2), then point the rollout at the robot instead of the sim:
|
||||
|
||||
```bash
|
||||
lerobot-rollout \
|
||||
--strategy.type=base \
|
||||
--policy.path=nepyope/sonic_walk \
|
||||
--policy.device=cuda \
|
||||
--robot.type=unitree_g1 \
|
||||
--robot.is_simulation=false \
|
||||
--robot.robot_ip=<ROBOT_IP> \
|
||||
--robot.controller=SonicWholeBodyController \
|
||||
--robot.cameras='{"ego_view": {"type": "zmq", "server_address": "<ROBOT_IP>", "port": 5555, "camera_name": "head_camera", "width": 640, "height": 480, "fps": 30, "warmup_s": 5}}'
|
||||
```
|
||||
|
||||
On connect, the robot eases every joint to the decoder's `default_angles` before the controller takes over, so the first policy commands don't snap from the connect-time pose.
|
||||
|
||||
---
|
||||
|
||||
## Additional Resources
|
||||
|
||||
- [Unitree SDK Documentation](https://github.com/unitreerobotics/unitree_sdk2_python)
|
||||
@@ -341,4 +300,4 @@ On connect, the robot eases every joint to the decoder's `default_angles` before
|
||||
|
||||
---
|
||||
|
||||
_Last updated: July 2026_
|
||||
_Last updated: March 2026_
|
||||
|
||||
@@ -11,9 +11,10 @@ LeRobot provides several utilities for manipulating datasets:
|
||||
3. **Merge Datasets** - Combine multiple datasets into one. The datasets must have identical features, and episodes are concatenated in the order specified in `repo_ids`
|
||||
4. **Add Features** - Add new features to a dataset
|
||||
5. **Remove Features** - Remove features from a dataset
|
||||
6. **Convert to Video** - Convert image-based datasets to video format for efficient storage (RGB and depth cameras are encoded with separate encoders)
|
||||
7. **Re-encode Videos** - Re-encode an existing video dataset's RGB and/or depth streams with new encoder settings
|
||||
8. **Show the Info of Datasets** - Show the summary of datasets information such as number of episode etc.
|
||||
6. **Modify Tasks** - Change the natural-language task descriptions associated with episodes
|
||||
7. **Convert to Video** - Convert image-based datasets to video format for efficient storage (RGB and depth cameras are encoded with separate encoders)
|
||||
8. **Re-encode Videos** - Re-encode an existing video dataset's RGB and/or depth streams with new encoder settings
|
||||
9. **Show the Info of Datasets** - Show the summary of datasets information such as number of episode etc.
|
||||
|
||||
The core implementation is in `lerobot.datasets.dataset_tools`.
|
||||
An example script detailing how to use the tools API is available in `examples/dataset/use_dataset_tools.py`.
|
||||
@@ -89,6 +90,53 @@ lerobot-edit-dataset \
|
||||
--operation.feature_names "['observation.images.top']"
|
||||
```
|
||||
|
||||
#### Modify Tasks
|
||||
|
||||
Change the natural-language task descriptions attached to episodes. This is useful for fixing typos, standardizing wording, or re-labeling episodes.
|
||||
|
||||
> [!WARNING]
|
||||
> `modify_tasks` modifies the dataset **in-place** (updating `meta/tasks.parquet`, the `task_index` column in the data files, the `tasks` column in the episode metadata, and `total_tasks` in `meta/info.json`). The `--new_repo_id` and `--new_root` parameters are ignored for this operation.
|
||||
|
||||
```bash
|
||||
# Set a single task for all episodes
|
||||
lerobot-edit-dataset \
|
||||
--repo_id lerobot/pusht \
|
||||
--operation.type modify_tasks \
|
||||
--operation.new_task "Pick up the cube and place it"
|
||||
|
||||
# Set different tasks for specific episodes
|
||||
lerobot-edit-dataset \
|
||||
--repo_id lerobot/pusht \
|
||||
--operation.type modify_tasks \
|
||||
--operation.episode_tasks '{"0": "Task A", "1": "Task B", "2": "Task A"}'
|
||||
|
||||
# Replace existing task strings wherever they appear
|
||||
lerobot-edit-dataset \
|
||||
--repo_id lerobot/pusht \
|
||||
--operation.type modify_tasks \
|
||||
--operation.task_replacements '{"Pick up the red cube": "Lift the red cube"}'
|
||||
|
||||
# Combine modes in a single run
|
||||
lerobot-edit-dataset \
|
||||
--repo_id lerobot/pusht \
|
||||
--operation.type modify_tasks \
|
||||
--operation.new_task "Default task" \
|
||||
--operation.task_replacements '{"Pick up the red cube": "Lift the red cube"}' \
|
||||
--operation.episode_tasks '{"5": "Special task for episode 5"}'
|
||||
```
|
||||
|
||||
**Parameters:**
|
||||
|
||||
- `new_task`: A single task string used as the default for episodes not otherwise covered.
|
||||
- `episode_tasks`: Mapping from episode index to task string.
|
||||
- `task_replacements`: Mapping from existing task strings to their replacements, applied to episodes whose current task matches a key. Every key must be an existing task in the dataset.
|
||||
|
||||
The modes can be combined in a single run. Per episode, the task is resolved with the following precedence:
|
||||
|
||||
`episode_tasks` > `task_replacements` > `new_task` > original task
|
||||
|
||||
At least one of `new_task`, `episode_tasks`, or `task_replacements` must be specified. An episode that ends up with no task raises an error.
|
||||
|
||||
#### Convert to Video
|
||||
|
||||
Convert an image-based dataset to video format, creating a new LeRobotDataset where images are stored as videos. This is useful for reducing storage requirements and improving data loading performance. The new dataset will have the exact same structure as the original, but with images encoded as MP4 videos in the proper LeRobot format.
|
||||
|
||||
@@ -49,16 +49,16 @@ lerobot-record \
|
||||
|
||||
All flags below are prefixed with `--dataset.rgb_encoder.` on the CLI.
|
||||
|
||||
| Parameter | Type | Default | Description |
|
||||
| --------------- | ---------------- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `vcodec` | `str` | `"libsvtav1"` | Video codec name. `"auto"` picks the first available hardware encoder from a fixed preference list, falling back to `libsvtav1`. |
|
||||
| `pix_fmt` | `str` | `"yuv420p"` | Output pixel format. Must be supported by the chosen codec in your FFmpeg build. |
|
||||
| `g` | `int` | `2` | GOP size — a keyframe every `g` frames. Emitted as FFmpeg option `g`. |
|
||||
| `crf` | `int` or `float` | `30` | Abstract quality value, mapped per codec (see the [mapping](#mapping-videoencoderconfig--ffmpeg-options) below). Lower → higher quality / larger output where the mapping is monotone. |
|
||||
| `preset` | `int` or `str` | `12` \* | Encoder speed preset; meaning depends on the codec. <br/>\* When unset and `vcodec=libsvtav1`, LeRobot defaults to `12`. |
|
||||
| `fast_decode` | `int` | `0` | `libsvtav1`: `0–2`, passed via `svtav1-params`. <br/>`h264` / `hevc` (software): if `>0`, sets `tune=fastdecode`. <br/>Other codecs: usually unused. |
|
||||
| `video_backend` | `str` | `"pyav"` | Only `"pyav"` is currently implemented for video encoding. |
|
||||
| `extra_options` | `dict` | `{}` | Extra FFmpeg or codec specific options merged after the structured fields above. Cannot override keys already set by those fields. |
|
||||
| Parameter | Type | Default | Description |
|
||||
| --------------- | ---------------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `vcodec` | `str` | `"libsvtav1"` | Video codec name. `"auto"` picks the first available hardware encoder from a fixed preference list, falling back to `libsvtav1`. |
|
||||
| `pix_fmt` | `str` | `"yuv420p"` | Output pixel format. Must be supported by the chosen codec in your FFmpeg build. |
|
||||
| `g` | `int` | `2` | GOP size — a keyframe every `g` frames. Emitted as FFmpeg option `g`. |
|
||||
| `crf` | `int` or `float` | `30` | Abstract quality value, mapped per codec (see the [mapping](https://github.com/huggingface/lerobot/blob/main/src/lerobot/configs/video.py#L197)). Lower → higher quality / larger output where the mapping is monotone. |
|
||||
| `preset` | `int` or `str` | `12` \* | Encoder speed preset; meaning depends on the codec. <br/>\* When unset and `vcodec=libsvtav1`, LeRobot defaults to `12`. |
|
||||
| `fast_decode` | `int` | `0` | `libsvtav1`: `0–2`, passed via `svtav1-params`. <br/>`h264` / `hevc` (software): if `>0`, sets `tune=fastdecode`. <br/>Other codecs: usually unused. |
|
||||
| `video_backend` | `str` | `"pyav"` | Only `"pyav"` is currently implemented for video encoding. |
|
||||
| `extra_options` | `dict` | `{}` | Extra FFmpeg or codec specific options merged after the structured fields above. Cannot override keys already set by those fields. |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -44,6 +44,7 @@ from typing import Protocol
|
||||
|
||||
import numpy as np
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -56,7 +57,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
EEBoundsAndSafety,
|
||||
InverseKinematicsEEToJoints,
|
||||
)
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import HF_LEROBOT_CALIBRATION, HF_LEROBOT_HOME, TELEOPERATORS
|
||||
from lerobot.utils.robot_utils import precise_sleep
|
||||
|
||||
|
||||
@@ -38,7 +38,7 @@ from typing import TYPE_CHECKING
|
||||
|
||||
import numpy as np
|
||||
|
||||
from lerobot.types import RobotAction
|
||||
from lerobot.lerobot_types import RobotAction
|
||||
|
||||
from .base import _GRIPPER_MOTOR_SCALE, IsaacTeleopTeleoperator, _isaacteleop_available
|
||||
from .config_isaac_teleop import SO101LeaderArmConfig
|
||||
|
||||
@@ -32,7 +32,7 @@ from typing import TYPE_CHECKING, Any
|
||||
|
||||
import numpy as np
|
||||
|
||||
from lerobot.types import RobotAction
|
||||
from lerobot.lerobot_types import RobotAction
|
||||
|
||||
from .base import IsaacTeleopTeleoperator, _isaacteleop_available
|
||||
from .config_isaac_teleop import XRControllerConfig
|
||||
|
||||
@@ -26,8 +26,8 @@ from __future__ import annotations
|
||||
from dataclasses import dataclass
|
||||
|
||||
from lerobot.configs.types import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import RobotAction
|
||||
from lerobot.processor import ProcessorStepRegistry, RobotActionProcessorStep
|
||||
from lerobot.types import RobotAction
|
||||
from lerobot.utils.rotation import Rotation
|
||||
|
||||
from .base import _GRIPPER_MOTOR_SCALE
|
||||
|
||||
@@ -21,6 +21,7 @@ from lerobot.cameras.opencv import OpenCVCameraConfig
|
||||
from lerobot.common.control_utils import predict_action
|
||||
from lerobot.configs import FeatureType, PolicyFeature
|
||||
from lerobot.datasets import LeRobotDataset, aggregate_pipeline_dataset_features, create_initial_features
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.policies import make_pre_post_processors
|
||||
from lerobot.policies.act import ACTPolicy
|
||||
@@ -38,7 +39,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
ForwardKinematicsJointsToEE,
|
||||
InverseKinematicsEEToJoints,
|
||||
)
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION, OBS_STR
|
||||
from lerobot.utils.feature_utils import build_dataset_frame, combine_feature_dicts
|
||||
from lerobot.utils.keyboard_input import init_keyboard_listener
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
|
||||
from lerobot.cameras.opencv import OpenCVCameraConfig
|
||||
from lerobot.datasets import LeRobotDataset, aggregate_pipeline_dataset_features, create_initial_features
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -36,7 +37,6 @@ from lerobot.scripts.lerobot_record import record_loop
|
||||
from lerobot.teleoperators.phone import Phone, PhoneConfig
|
||||
from lerobot.teleoperators.phone.config_phone import PhoneOS
|
||||
from lerobot.teleoperators.phone.phone_processor import MapPhoneActionToRobotAction
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.feature_utils import combine_feature_dicts
|
||||
from lerobot.utils.keyboard_input import init_keyboard_listener
|
||||
from lerobot.utils.utils import log_say
|
||||
|
||||
@@ -17,6 +17,7 @@
|
||||
import time
|
||||
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -27,7 +28,6 @@ from lerobot.robots.so_follower import SO100Follower, SO100FollowerConfig
|
||||
from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
InverseKinematicsEEToJoints,
|
||||
)
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION
|
||||
from lerobot.utils.robot_utils import precise_sleep
|
||||
from lerobot.utils.utils import log_say
|
||||
|
||||
@@ -27,6 +27,7 @@ Highlight, or DAgger via ``lerobot-rollout --strategy.type=...``.
|
||||
|
||||
from lerobot.cameras.opencv import OpenCVCameraConfig
|
||||
from lerobot.configs import PreTrainedConfig
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -43,7 +44,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
from lerobot.rollout import BaseStrategyConfig, RolloutConfig, build_rollout_context
|
||||
from lerobot.rollout.inference import SyncInferenceConfig
|
||||
from lerobot.rollout.strategies import BaseStrategy
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.process import ProcessSignalHandler
|
||||
from lerobot.utils.utils import init_logging
|
||||
|
||||
|
||||
@@ -15,6 +15,7 @@
|
||||
|
||||
import time
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -31,7 +32,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
from lerobot.teleoperators.phone import Phone, PhoneConfig
|
||||
from lerobot.teleoperators.phone.config_phone import PhoneOS
|
||||
from lerobot.teleoperators.phone.phone_processor import MapPhoneActionToRobotAction
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.robot_utils import precise_sleep
|
||||
from lerobot.utils.visualization_utils import init_rerun, log_rerun_data
|
||||
|
||||
|
||||
@@ -417,7 +417,7 @@ class RTCEvaluator:
|
||||
def run_evaluation(self):
|
||||
"""Run evaluation on two random dataset samples using three separate policies.
|
||||
|
||||
Note: Policies are deinitalized after each step to free memory. Large models
|
||||
Note: Policies are deinitialized after each step to free memory. Large models
|
||||
(e.g., VLA models with billions of parameters) cannot fit three instances in
|
||||
memory simultaneously. By deleting and garbage collecting after each step,
|
||||
we ensure only one policy is loaded at a time.
|
||||
|
||||
@@ -21,6 +21,7 @@ from lerobot.cameras.opencv import OpenCVCameraConfig
|
||||
from lerobot.common.control_utils import predict_action
|
||||
from lerobot.configs import FeatureType, PolicyFeature
|
||||
from lerobot.datasets import LeRobotDataset, aggregate_pipeline_dataset_features, create_initial_features
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.policies import make_pre_post_processors
|
||||
from lerobot.policies.act import ACTPolicy
|
||||
@@ -38,7 +39,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
ForwardKinematicsJointsToEE,
|
||||
InverseKinematicsEEToJoints,
|
||||
)
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION, OBS_STR
|
||||
from lerobot.utils.feature_utils import build_dataset_frame, combine_feature_dicts
|
||||
from lerobot.utils.keyboard_input import init_keyboard_listener
|
||||
|
||||
@@ -17,6 +17,7 @@
|
||||
|
||||
from lerobot.cameras.opencv import OpenCVCameraConfig
|
||||
from lerobot.datasets import LeRobotDataset, aggregate_pipeline_dataset_features, create_initial_features
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -33,7 +34,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
)
|
||||
from lerobot.scripts.lerobot_record import record_loop
|
||||
from lerobot.teleoperators.so_leader import SO100Leader, SO100LeaderConfig
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.feature_utils import combine_feature_dicts
|
||||
from lerobot.utils.keyboard_input import init_keyboard_listener
|
||||
from lerobot.utils.utils import log_say
|
||||
|
||||
@@ -18,6 +18,7 @@
|
||||
import time
|
||||
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -28,7 +29,6 @@ from lerobot.robots.so_follower import SO100Follower, SO100FollowerConfig
|
||||
from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
InverseKinematicsEEToJoints,
|
||||
)
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION
|
||||
from lerobot.utils.robot_utils import precise_sleep
|
||||
from lerobot.utils.utils import log_say
|
||||
|
||||
@@ -25,6 +25,7 @@ forward/inverse kinematics.
|
||||
|
||||
from lerobot.cameras.opencv import OpenCVCameraConfig
|
||||
from lerobot.configs import PreTrainedConfig
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -41,7 +42,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
from lerobot.rollout import BaseStrategyConfig, RolloutConfig, build_rollout_context
|
||||
from lerobot.rollout.inference import SyncInferenceConfig
|
||||
from lerobot.rollout.strategies import BaseStrategy
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.process import ProcessSignalHandler
|
||||
from lerobot.utils.utils import init_logging
|
||||
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
|
||||
import time
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -30,7 +31,6 @@ from lerobot.robots.so_follower.robot_kinematic_processor import (
|
||||
InverseKinematicsEEToJoints,
|
||||
)
|
||||
from lerobot.teleoperators.so_leader import SO100Leader, SO100LeaderConfig
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.robot_utils import precise_sleep
|
||||
from lerobot.utils.visualization_utils import init_rerun, log_rerun_data
|
||||
|
||||
|
||||
+3
-3
@@ -67,8 +67,8 @@ dependencies = [
|
||||
"einops>=0.8.0,<0.9.0",
|
||||
|
||||
# Config & Hub
|
||||
"draccus==0.10.0", # TODO: Relax version constraint
|
||||
"huggingface-hub>=1.0.0,<2.0.0",
|
||||
"draccus>=0.11.6,<0.12.0",
|
||||
"huggingface-hub>=1.6.0,<2.0.0",
|
||||
"requests>=2.32.0,<3.0.0",
|
||||
|
||||
# Environments
|
||||
@@ -95,7 +95,7 @@ dependencies = [
|
||||
|
||||
# ── Feature-scoped extras ──────────────────────────────────
|
||||
dataset = [
|
||||
"datasets>=4.7.0,<5.0.0",
|
||||
"datasets>=4.8.0,<5.0.0",
|
||||
"pandas>=2.0.0,<3.0.0", # NOTE: Transitive dependency of datasets
|
||||
"pyarrow>=21.0.0,<30.0.0", # NOTE: Transitive dependency of datasets
|
||||
"lerobot[av-dep]",
|
||||
|
||||
@@ -38,6 +38,7 @@ import draccus
|
||||
import grpc
|
||||
import torch
|
||||
|
||||
from lerobot.lerobot_types import PolicyAction
|
||||
from lerobot.policies import get_policy_class, make_pre_post_processors
|
||||
from lerobot.processor import PolicyProcessorPipeline
|
||||
from lerobot.transport import (
|
||||
@@ -45,7 +46,6 @@ from lerobot.transport import (
|
||||
services_pb2_grpc, # type: ignore
|
||||
)
|
||||
from lerobot.transport.utils import receive_bytes_in_chunks
|
||||
from lerobot.types import PolicyAction
|
||||
|
||||
from .configs import PolicyServerConfig
|
||||
from .constants import SUPPORTED_POLICIES
|
||||
|
||||
@@ -365,11 +365,12 @@ class RealSenseCamera(Camera):
|
||||
return self._async_read(timeout_ms=10000, read_depth=read_depth)
|
||||
|
||||
def _get_color_sensor(self) -> "rs.sensor":
|
||||
"""Returns the sensor that controls the color stream.
|
||||
"""Returns the dedicated "RGB Camera" sensor that controls the color stream.
|
||||
|
||||
Most RealSense cameras expose "RGB Camera" for color. The D405 has no
|
||||
separate RGB module — its color stream comes from "Stereo Module".
|
||||
We try RGB Camera first, then fall back to Stereo Module.
|
||||
Manual color controls are only applied to a dedicated RGB module. Cameras
|
||||
without one (e.g. the D405, whose color stream comes from the shared
|
||||
"Stereo Module") are unsupported, so we never fall back to another sensor
|
||||
to avoid altering the depth stream.
|
||||
"""
|
||||
if self.rs_profile is None:
|
||||
raise RuntimeError(f"{self}: rs_profile must be initialized before use.")
|
||||
@@ -377,12 +378,14 @@ class RealSenseCamera(Camera):
|
||||
device = self.rs_profile.get_device()
|
||||
sensors = {s.get_info(rs.camera_info.name): s for s in device.query_sensors()}
|
||||
|
||||
for name in ("RGB Camera", "Stereo Module"):
|
||||
if name in sensors:
|
||||
return sensors[name]
|
||||
if "RGB Camera" in sensors:
|
||||
return sensors["RGB Camera"]
|
||||
|
||||
available = list(sensors.keys())
|
||||
raise RuntimeError(f"{self}: no color sensor found. Available sensors: {available}")
|
||||
raise RuntimeError(
|
||||
f"{self}: manual color controls require a dedicated 'RGB Camera' module, which this camera does not have. ",
|
||||
f"Available sensors: {available}.",
|
||||
)
|
||||
|
||||
def _set_sensor_option(self, sensor: "rs.sensor", option: "rs.option", value: float, label: str) -> None:
|
||||
"""Sets a sensor option, re-raising range errors with actionable diagnostics."""
|
||||
|
||||
@@ -35,9 +35,9 @@ else:
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
from lerobot.lerobot_types import PolicyAction
|
||||
from lerobot.processor import PolicyProcessorPipeline
|
||||
from lerobot.robots import Robot
|
||||
from lerobot.types import PolicyAction
|
||||
|
||||
|
||||
def predict_action(
|
||||
|
||||
@@ -52,6 +52,17 @@ def get_step_checkpoint_dir(output_dir: Path, total_steps: int, step: int) -> Pa
|
||||
return output_dir / CHECKPOINTS_DIR / step_identifier
|
||||
|
||||
|
||||
def should_save_checkpoint(step: int, save_freq: int, total_steps: int) -> bool:
|
||||
"""Whether a checkpoint should be saved at ``step``.
|
||||
|
||||
A checkpoint is saved every ``save_freq`` steps and always after the final step. A
|
||||
non-positive ``save_freq`` disables periodic saving (only the final checkpoint is
|
||||
written), mirroring how ``log_freq``/``eval_freq`` treat non-positive values and
|
||||
avoiding a ``ZeroDivisionError`` from ``step % 0``.
|
||||
"""
|
||||
return (save_freq > 0 and step % save_freq == 0) or step == total_steps
|
||||
|
||||
|
||||
def save_training_step(
|
||||
step: int, save_dir: Path, num_processes: int | None = None, batch_size: int | None = None
|
||||
) -> None:
|
||||
|
||||
+145
-29
@@ -27,6 +27,13 @@ from typing import Any, TypeVar, cast
|
||||
|
||||
import draccus
|
||||
import yaml # type: ignore[import-untyped]
|
||||
from draccus.help_formatter import SimpleHelpFormatter
|
||||
from draccus.utils import DecodingError
|
||||
from draccus.wrappers import DataclassWrapper
|
||||
from draccus.wrappers.choice_wrapper import ChoiceWrapper, UnionWrapper
|
||||
from draccus.wrappers.field_wrapper import FieldWrapper
|
||||
from draccus.wrappers.suppressing_argparse import SuppressingArgumentParser
|
||||
from draccus.wrappers.wrapper import AggregateWrapper, Wrapper
|
||||
|
||||
from lerobot.utils.utils import has_method
|
||||
|
||||
@@ -72,11 +79,18 @@ def get_cli_overrides(field_name: str, args: Sequence[str] | None = None) -> lis
|
||||
args = sys.argv[1:]
|
||||
attr_level_args = []
|
||||
detect_string = f"--{field_name}."
|
||||
exclude_strings = (f"--{field_name}.{draccus.CHOICE_TYPE_KEY}=", f"--{field_name}.{PATH_KEY}=")
|
||||
for arg in args:
|
||||
if arg.startswith(detect_string) and not arg.startswith(exclude_strings):
|
||||
denested_arg = f"--{arg.removeprefix(detect_string)}"
|
||||
attr_level_args.append(denested_arg)
|
||||
excluded_names = (draccus.CHOICE_TYPE_KEY, PATH_KEY)
|
||||
for index, arg in enumerate(args):
|
||||
if not arg.startswith(detect_string):
|
||||
continue
|
||||
|
||||
denested_arg = arg.removeprefix(detect_string)
|
||||
if denested_arg.split("=", maxsplit=1)[0] in excluded_names:
|
||||
continue
|
||||
|
||||
attr_level_args.append(f"--{denested_arg}")
|
||||
if "=" not in arg and index + 1 < len(args) and not args[index + 1].startswith("--"):
|
||||
attr_level_args.append(args[index + 1])
|
||||
|
||||
return attr_level_args
|
||||
|
||||
@@ -84,10 +98,12 @@ def get_cli_overrides(field_name: str, args: Sequence[str] | None = None) -> lis
|
||||
def parse_arg(arg_name: str, args: Sequence[str] | None = None) -> str | None:
|
||||
if args is None:
|
||||
args = sys.argv[1:]
|
||||
prefix = f"--{arg_name}="
|
||||
for arg in args:
|
||||
if arg.startswith(prefix):
|
||||
return arg[len(prefix) :]
|
||||
option = f"--{arg_name}"
|
||||
for index, arg in enumerate(args):
|
||||
if arg.startswith(f"{option}="):
|
||||
return arg.removeprefix(f"{option}=")
|
||||
if arg == option and index + 1 < len(args) and not args[index + 1].startswith("--"):
|
||||
return args[index + 1]
|
||||
return None
|
||||
|
||||
|
||||
@@ -95,7 +111,7 @@ def parse_plugin_args(plugin_arg_suffix: str, args: Sequence[str]) -> dict[str,
|
||||
"""Parse plugin-related arguments from command-line arguments.
|
||||
|
||||
This function extracts arguments from command-line arguments that match a specified suffix pattern.
|
||||
It processes arguments in the format '--key=value' and returns them as a dictionary.
|
||||
It accepts arguments in the formats '--key=value' and '--key value' and returns them as a dictionary.
|
||||
|
||||
Args:
|
||||
plugin_arg_suffix (str): The suffix to identify plugin-related arguments.
|
||||
@@ -112,13 +128,18 @@ def parse_plugin_args(plugin_arg_suffix: str, args: Sequence[str]) -> dict[str,
|
||||
{'env.discover_packages_path': 'my_package'}
|
||||
"""
|
||||
plugin_args = {}
|
||||
for arg in args:
|
||||
if "=" in arg and plugin_arg_suffix in arg:
|
||||
key, value = arg.split("=", 1)
|
||||
# Remove leading '--' if present
|
||||
if key.startswith("--"):
|
||||
key = key[2:]
|
||||
plugin_args[key] = value
|
||||
for index, arg in enumerate(args):
|
||||
if not arg.startswith("--"):
|
||||
continue
|
||||
|
||||
key, separator, value = arg[2:].partition("=")
|
||||
if plugin_arg_suffix not in key:
|
||||
continue
|
||||
if not separator:
|
||||
if index + 1 >= len(args) or args[index + 1].startswith("--"):
|
||||
continue
|
||||
value = args[index + 1]
|
||||
plugin_args[key] = value
|
||||
return plugin_args
|
||||
|
||||
|
||||
@@ -185,10 +206,82 @@ def get_type_arg(field_name: str, args: Sequence[str] | None = None) -> str | No
|
||||
return parse_arg(f"{field_name}.{draccus.CHOICE_TYPE_KEY}", args)
|
||||
|
||||
|
||||
def _register_scoped_actions(
|
||||
wrapper: Wrapper, parser: SuppressingArgumentParser, cli_args: Sequence[str]
|
||||
) -> None:
|
||||
"""Like draccus's own Wrapper.register_actions, but for a ChoiceType field only recurses into
|
||||
the already-selected subclass (per CLI `.type` args), instead of every registered choice.
|
||||
|
||||
This mirrors draccus 0.11.x's internal wrapper traversal because its public parser eagerly registers
|
||||
every choice before parsing the command line. Keep this in sync when updating draccus.
|
||||
"""
|
||||
if isinstance(wrapper, ChoiceWrapper):
|
||||
group = parser.add_argument_group(title=wrapper.title, description=wrapper.description)
|
||||
children = wrapper._children
|
||||
arg_name = f"{wrapper.dest}.{draccus.CHOICE_TYPE_KEY}" if wrapper.dest else draccus.CHOICE_TYPE_KEY
|
||||
group.add_argument(
|
||||
f"--{arg_name}",
|
||||
choices=list(children.keys()),
|
||||
help=f"Which type of {wrapper.title} to use",
|
||||
required=wrapper.required,
|
||||
)
|
||||
selected = get_type_arg(wrapper.dest, cli_args) if wrapper.dest else None
|
||||
if selected in children:
|
||||
_register_scoped_actions(children[selected], parser, cli_args)
|
||||
elif isinstance(wrapper, DataclassWrapper):
|
||||
group = parser.add_argument_group(title=wrapper.title, description=wrapper.description)
|
||||
for child in wrapper._children:
|
||||
if isinstance(child, AggregateWrapper):
|
||||
parser.add_argument(
|
||||
f"--{child.name}", type=str, required=False, help=f"Config file for {child.name}"
|
||||
)
|
||||
_register_scoped_actions(child, parser, cli_args)
|
||||
elif isinstance(child, FieldWrapper):
|
||||
child.add_action(group)
|
||||
elif isinstance(wrapper, UnionWrapper):
|
||||
group = parser.add_argument_group(title=wrapper.title, description=wrapper.description)
|
||||
has_field_wrapper = False
|
||||
for child in wrapper._children:
|
||||
if isinstance(child, (DataclassWrapper, ChoiceWrapper)):
|
||||
_register_scoped_actions(child, parser, cli_args)
|
||||
elif isinstance(child, FieldWrapper):
|
||||
has_field_wrapper = True
|
||||
if has_field_wrapper:
|
||||
group.add_argument(f"--{wrapper.dest}", required=False)
|
||||
else:
|
||||
wrapper.register_actions(parser)
|
||||
|
||||
|
||||
def print_scoped_help(config_class: type, cli_args: Sequence[str]) -> None:
|
||||
"""Prints --help output scoped to the choices already resolved on the CLI (e.g. --env.type=pusht),
|
||||
instead of draccus's default of expanding every registered subclass of every ChoiceType field."""
|
||||
parser = SuppressingArgumentParser(formatter_class=SimpleHelpFormatter)
|
||||
parser.add_argument(
|
||||
f"--{draccus.utils.CONFIG_ARG}", type=str, help="Path for a config file to parse with draccus"
|
||||
)
|
||||
_register_scoped_actions(DataclassWrapper(config_class), parser, cli_args)
|
||||
parser.print_help()
|
||||
|
||||
|
||||
def filter_arg(field_to_filter: str, args: Sequence[str] | None = None) -> list[str]:
|
||||
if args is None:
|
||||
return []
|
||||
return [arg for arg in args if not arg.startswith(f"--{field_to_filter}=")]
|
||||
option = f"--{field_to_filter}"
|
||||
filtered_args = []
|
||||
index = 0
|
||||
while index < len(args):
|
||||
arg = args[index]
|
||||
if arg == option:
|
||||
index += 1
|
||||
if index < len(args) and not args[index].startswith("--"):
|
||||
index += 1
|
||||
continue
|
||||
if arg.startswith(f"{option}="):
|
||||
index += 1
|
||||
continue
|
||||
filtered_args.append(arg)
|
||||
index += 1
|
||||
return filtered_args
|
||||
|
||||
|
||||
def filter_path_args(fields_to_filter: str | list[str], args: Sequence[str] | None = None) -> list[str]:
|
||||
@@ -220,7 +313,23 @@ def filter_path_args(fields_to_filter: str | list[str], args: Sequence[str] | No
|
||||
argument=None,
|
||||
message=f"Cannot specify both --{field}.{PATH_KEY} and --{field}.{draccus.CHOICE_TYPE_KEY}",
|
||||
)
|
||||
filtered_args = [arg for arg in filtered_args if not arg.startswith(f"--{field}.")]
|
||||
option_prefix = f"--{field}."
|
||||
retained_args = []
|
||||
index = 0
|
||||
while index < len(filtered_args):
|
||||
arg = filtered_args[index]
|
||||
if arg.startswith(option_prefix):
|
||||
index += 1
|
||||
if (
|
||||
"=" not in arg
|
||||
and index < len(filtered_args)
|
||||
and not filtered_args[index].startswith("--")
|
||||
):
|
||||
index += 1
|
||||
continue
|
||||
retained_args.append(arg)
|
||||
index += 1
|
||||
filtered_args = retained_args
|
||||
|
||||
return filtered_args
|
||||
|
||||
@@ -299,6 +408,9 @@ def wrap(config_path: Path | None = None) -> Callable[[F], F]:
|
||||
# add the relevant CLI arg to the error message
|
||||
raise PluginLoadError(f"{e}\nFailed plugin CLI Arg: {plugin_cli_arg}") from e
|
||||
cli_args = filter_arg(plugin_cli_arg, cli_args)
|
||||
if "--help" in cli_args or "-h" in cli_args:
|
||||
print_scoped_help(argtype, cli_args)
|
||||
sys.exit(0)
|
||||
config_path_cli = parse_arg("config_path", cli_args)
|
||||
if has_method(argtype, "__get_path_fields__"):
|
||||
path_fields = argtype.__get_path_fields__()
|
||||
@@ -306,17 +418,21 @@ def wrap(config_path: Path | None = None) -> Callable[[F], F]:
|
||||
# Also extract path fields from the YAML/JSON config file
|
||||
if config_path_cli:
|
||||
config_path_cli = extract_path_fields_from_config(config_path_cli, path_fields)
|
||||
if has_method(argtype, "from_pretrained") and config_path_cli:
|
||||
cli_args = filter_arg("config_path", cli_args)
|
||||
cfg = argtype.from_pretrained(config_path_cli, cli_args=cli_args)
|
||||
else:
|
||||
if config_path_cli:
|
||||
try:
|
||||
if has_method(argtype, "from_pretrained") and config_path_cli:
|
||||
cli_args = filter_arg("config_path", cli_args)
|
||||
cfg = draccus.parse(
|
||||
config_class=argtype,
|
||||
config_path=config_path_cli or config_path,
|
||||
args=cli_args,
|
||||
)
|
||||
cfg = argtype.from_pretrained(config_path_cli, cli_args=cli_args)
|
||||
else:
|
||||
if config_path_cli:
|
||||
cli_args = filter_arg("config_path", cli_args)
|
||||
cfg = draccus.parse(
|
||||
config_class=argtype,
|
||||
config_path=config_path_cli or config_path,
|
||||
args=cli_args,
|
||||
)
|
||||
except DecodingError as e:
|
||||
print(f"error: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
response = fn(cfg, *args, **kwargs)
|
||||
return response
|
||||
|
||||
|
||||
@@ -163,8 +163,10 @@ class PreTrainedConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC): # type: igno
|
||||
return None
|
||||
|
||||
def _save_pretrained(self, save_directory: Path) -> None:
|
||||
with open(save_directory / CONFIG_NAME, "w") as f, draccus.config_type("json"):
|
||||
draccus.dump(self, f, indent=4)
|
||||
# Encode against the base class so draccus includes the choice "type" key,
|
||||
# which `from_pretrained` needs to resolve the concrete subclass.
|
||||
with open(save_directory / CONFIG_NAME, "w") as f:
|
||||
json.dump(draccus.encode(self, PreTrainedConfig), f, indent=4)
|
||||
|
||||
@classmethod
|
||||
def from_pretrained(
|
||||
|
||||
@@ -103,8 +103,10 @@ class RewardModelConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC):
|
||||
pass
|
||||
|
||||
def _save_pretrained(self, save_directory: Path) -> None:
|
||||
with open(save_directory / CONFIG_NAME, "w") as f, draccus.config_type("json"):
|
||||
draccus.dump(self, f, indent=4)
|
||||
# Encode against the base class so draccus includes the choice "type" key,
|
||||
# which `from_pretrained` needs to resolve the concrete subclass.
|
||||
with open(save_directory / CONFIG_NAME, "w") as f:
|
||||
json.dump(draccus.encode(self, RewardModelConfig), f, indent=4)
|
||||
|
||||
@classmethod
|
||||
def from_pretrained(
|
||||
|
||||
@@ -119,6 +119,7 @@ class TrainPipelineConfig(HubMixin):
|
||||
tolerance_s: float = 1e-4
|
||||
save_checkpoint: bool = True
|
||||
# Checkpoint is saved every `save_freq` training iterations and after the last training step.
|
||||
# A non-positive value disables periodic saving, keeping only the final checkpoint.
|
||||
save_freq: int = 20_000
|
||||
use_policy_training_preset: bool = True
|
||||
optimizer: OptimizerConfig | None = None
|
||||
@@ -194,7 +195,11 @@ class TrainPipelineConfig(HubMixin):
|
||||
)
|
||||
|
||||
if Path(config_path).resolve().exists():
|
||||
policy_dir = Path(config_path).parent
|
||||
# `config_path` may point at the checkpoint's train_config.json or at its
|
||||
# pretrained_model/ directory (both documented above) — resolve either to
|
||||
# the pretrained_model/ directory.
|
||||
config_path_obj = Path(config_path)
|
||||
policy_dir = config_path_obj.parent if config_path_obj.is_file() else config_path_obj
|
||||
self.checkpoint_path = policy_dir.parent
|
||||
elif self.job.is_remote:
|
||||
return
|
||||
|
||||
@@ -18,13 +18,15 @@ import logging
|
||||
from collections.abc import Callable, Iterable
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
from typing import Literal
|
||||
|
||||
import numpy as np
|
||||
import packaging.version
|
||||
import pandas as pd
|
||||
import pyarrow as pa
|
||||
import pyarrow.parquet as pq
|
||||
from huggingface_hub import snapshot_download
|
||||
from huggingface_hub import snapshot_download, sync_bucket
|
||||
from huggingface_hub.utils import WeakFileLock
|
||||
|
||||
from lerobot.configs import DEPTH_METER_UNIT, VideoEncoderConfig
|
||||
from lerobot.utils.constants import DEFAULT_FEATURES, HF_LEROBOT_HOME, HF_LEROBOT_HUB_CACHE
|
||||
@@ -74,6 +76,7 @@ class LeRobotDatasetMetadata:
|
||||
force_cache_sync: bool = False,
|
||||
metadata_buffer_size: int = 10,
|
||||
*,
|
||||
repo_type: Literal["dataset", "bucket"] = "dataset",
|
||||
token: str | bool | None = None,
|
||||
):
|
||||
"""Load or download metadata for an existing LeRobot dataset.
|
||||
@@ -96,36 +99,53 @@ class LeRobotDatasetMetadata:
|
||||
even when local files exist.
|
||||
metadata_buffer_size: Number of episode metadata records to buffer
|
||||
in memory before flushing to parquet.
|
||||
repo_type: Repository type: "dataset" (default) or "bucket" for an
|
||||
HF Storage Bucket streamed over hf://buckets/.
|
||||
token: Authentication token used for Hub requests. Pass a string
|
||||
token, ``True`` to require the locally stored token, ``False``
|
||||
to disable authentication, or ``None`` to use the Hugging Face
|
||||
Hub default.
|
||||
"""
|
||||
if repo_type not in ("dataset", "bucket"):
|
||||
raise ValueError(f"repo_type must be 'dataset' or 'bucket', got {repo_type!r}")
|
||||
|
||||
self.repo_id = repo_id
|
||||
self.repo_type = repo_type
|
||||
self.revision = revision if revision else CODEBASE_VERSION
|
||||
self._requested_root = Path(root) if root is not None else None
|
||||
self.root = self._requested_root if self._requested_root is not None else HF_LEROBOT_HOME / repo_id
|
||||
if self._requested_root is not None:
|
||||
self.root = self._requested_root
|
||||
elif self.repo_type == "bucket":
|
||||
self.root = HF_LEROBOT_HUB_CACHE / ("buckets--" + self.repo_id.replace("/", "--"))
|
||||
else:
|
||||
self.root = HF_LEROBOT_HOME / repo_id
|
||||
self._pq_writer = None
|
||||
self.latest_episode = None
|
||||
self._metadata_buffer: list[dict] = []
|
||||
self._metadata_buffer_size = metadata_buffer_size
|
||||
self._finalized = False
|
||||
|
||||
try:
|
||||
if force_cache_sync or (
|
||||
self._requested_root is None and has_legacy_hub_download_metadata(self.root)
|
||||
):
|
||||
raise FileNotFoundError
|
||||
self._load_metadata()
|
||||
except (FileNotFoundError, NotADirectoryError):
|
||||
if is_valid_version(self.revision):
|
||||
if token is None:
|
||||
self.revision = get_safe_version(self.repo_id, self.revision)
|
||||
else:
|
||||
self.revision = get_safe_version(self.repo_id, self.revision, token=token)
|
||||
metadata_lock = contextlib.nullcontext()
|
||||
if self.repo_type == "bucket":
|
||||
self.root.parent.mkdir(parents=True, exist_ok=True)
|
||||
metadata_lock = WeakFileLock(self.root.parent / f".{self.root.name}.lock")
|
||||
|
||||
self._pull_from_repo(allow_patterns="meta/", token=token)
|
||||
self._load_metadata()
|
||||
with metadata_lock:
|
||||
try:
|
||||
if force_cache_sync or (
|
||||
self._requested_root is None and has_legacy_hub_download_metadata(self.root)
|
||||
):
|
||||
raise FileNotFoundError
|
||||
self._load_metadata()
|
||||
except (FileNotFoundError, NotADirectoryError):
|
||||
if self.repo_type != "bucket" and is_valid_version(self.revision):
|
||||
if token is None:
|
||||
self.revision = get_safe_version(self.repo_id, self.revision)
|
||||
else:
|
||||
self.revision = get_safe_version(self.repo_id, self.revision, token=token)
|
||||
|
||||
self._pull_from_repo(allow_patterns="meta/", token=token)
|
||||
self._load_metadata()
|
||||
|
||||
def _flush_metadata_buffer(self) -> None:
|
||||
"""Write all buffered episode metadata to parquet file."""
|
||||
@@ -154,6 +174,12 @@ class LeRobotDatasetMetadata:
|
||||
self._pq_writer = pq.ParquetWriter(
|
||||
path, schema=table.schema, compression="snappy", use_dictionary=True
|
||||
)
|
||||
else:
|
||||
# Column order in `combined_dict` follows the source episode dict's insertion
|
||||
# order, which can differ between batches (e.g. episodes originally stored in
|
||||
# different parquet shards with different column orders). Realign to the
|
||||
# writer's established schema so `write_table` doesn't reject a reordered match.
|
||||
table = table.select(self._pq_writer.schema.names)
|
||||
|
||||
self._pq_writer.write_table(table)
|
||||
|
||||
@@ -232,6 +258,16 @@ class LeRobotDatasetMetadata:
|
||||
*,
|
||||
token: str | bool | None = None,
|
||||
) -> None:
|
||||
if self.repo_type == "bucket":
|
||||
self.root.mkdir(parents=True, exist_ok=True)
|
||||
sync_bucket(
|
||||
f"hf://buckets/{self.repo_id}/meta",
|
||||
str(self.root / "meta"),
|
||||
delete=True,
|
||||
quiet=True,
|
||||
token=token,
|
||||
)
|
||||
return
|
||||
token_kwargs = {} if token is None else {"token": token}
|
||||
if self._requested_root is None:
|
||||
self.root = Path(
|
||||
@@ -262,6 +298,8 @@ class LeRobotDatasetMetadata:
|
||||
@property
|
||||
def url_root(self) -> str:
|
||||
"""Hugging Face Hub URL root for this dataset."""
|
||||
if self.repo_type == "bucket":
|
||||
return f"hf://buckets/{self.repo_id}"
|
||||
return f"hf://datasets/{self.repo_id}"
|
||||
|
||||
@property
|
||||
|
||||
@@ -1045,10 +1045,12 @@ def _copy_data_with_feature_changes(
|
||||
df[feature_name] = feature_values
|
||||
else:
|
||||
feature_slice = values[frame_idx:end_idx]
|
||||
if len(feature_slice.shape) > 1 and feature_slice.shape[1] == 1:
|
||||
if feature_slice.ndim == 1:
|
||||
df[feature_name] = feature_slice
|
||||
elif feature_slice.ndim == 2 and feature_slice.shape[1] == 1:
|
||||
df[feature_name] = feature_slice.flatten()
|
||||
else:
|
||||
df[feature_name] = feature_slice
|
||||
df[feature_name] = list(feature_slice)
|
||||
frame_idx = end_idx
|
||||
|
||||
# Write using the same chunk/file structure as source
|
||||
@@ -1435,15 +1437,18 @@ def modify_tasks(
|
||||
dataset: LeRobotDataset,
|
||||
new_task: str | None = None,
|
||||
episode_tasks: dict[int, str] | None = None,
|
||||
task_replacements: dict[str, str] | None = None,
|
||||
) -> LeRobotDataset:
|
||||
"""Modify tasks in a LeRobotDataset.
|
||||
|
||||
This function allows you to either:
|
||||
1. Set a single task for the entire dataset (using `new_task`)
|
||||
2. Set specific tasks for specific episodes (using `episode_tasks`)
|
||||
3. Replace existing task strings wherever they appear (using `task_replacements`)
|
||||
|
||||
You can combine both: `new_task` sets the default, and `episode_tasks` overrides
|
||||
specific episodes.
|
||||
Per episode, the task is resolved with precedence:
|
||||
`episode_tasks` > `task_replacements` > `new_task` > original task. An episode that ends
|
||||
up with no task (none of the above apply and it had no original task) raises an error.
|
||||
|
||||
The dataset is modified in-place, updating only the task-related files:
|
||||
- meta/tasks.parquet
|
||||
@@ -1453,11 +1458,14 @@ def modify_tasks(
|
||||
|
||||
Args:
|
||||
dataset: The source LeRobotDataset to modify.
|
||||
new_task: A single task string to apply to all episodes. If None and episode_tasks
|
||||
is also None, raises an error.
|
||||
episode_tasks: Optional dict mapping episode indices to their task strings.
|
||||
Overrides `new_task` for specific episodes.
|
||||
new_task: Default task applied to any episode not covered by `episode_tasks` or a
|
||||
matching `task_replacements` entry.
|
||||
episode_tasks: Optional dict mapping episode indices to task strings. Takes precedence
|
||||
over both `task_replacements` and `new_task`.
|
||||
task_replacements: Optional dict mapping existing task strings to new ones. Applied to
|
||||
episodes whose current task matches a key. Every key must be an existing task.
|
||||
|
||||
At least one of `new_task`, `episode_tasks`, or `task_replacements` must be provided.
|
||||
|
||||
Examples:
|
||||
Set a single task for all episodes:
|
||||
@@ -1475,11 +1483,17 @@ def modify_tasks(
|
||||
new_task="Default task",
|
||||
episode_tasks={5: "Special task for episode 5"}
|
||||
)
|
||||
"""
|
||||
if new_task is None and episode_tasks is None:
|
||||
raise ValueError("Must specify at least one of new_task or episode_tasks")
|
||||
|
||||
if episode_tasks is not None:
|
||||
Replace existing task strings in-place:
|
||||
dataset = modify_tasks(
|
||||
dataset,
|
||||
task_replacements={"Pick up the cube": "Lift the cube"}
|
||||
)
|
||||
"""
|
||||
if not new_task and not episode_tasks and not task_replacements:
|
||||
raise ValueError("Must specify at least one of new_task, episode_tasks, or task_replacements")
|
||||
|
||||
if episode_tasks:
|
||||
valid_indices = set(range(dataset.meta.total_episodes))
|
||||
invalid = set(episode_tasks.keys()) - valid_indices
|
||||
if invalid:
|
||||
@@ -1489,19 +1503,29 @@ def modify_tasks(
|
||||
if dataset.meta.episodes is None:
|
||||
dataset.meta.episodes = load_episodes(dataset.root)
|
||||
|
||||
if task_replacements:
|
||||
current_tasks = set(dataset.meta.tasks.index)
|
||||
invalid_tasks = set(task_replacements) - current_tasks
|
||||
if invalid_tasks:
|
||||
raise ValueError(f"Task replacements reference unknown tasks: {sorted(invalid_tasks)}")
|
||||
|
||||
# Build the mapping from episode index to task string
|
||||
episode_to_task: dict[int, str] = {}
|
||||
for ep_idx in range(dataset.meta.total_episodes):
|
||||
original_tasks = dataset.meta.episodes[ep_idx]["tasks"]
|
||||
original_task = original_tasks[0] if original_tasks else None
|
||||
|
||||
if episode_tasks and ep_idx in episode_tasks:
|
||||
episode_to_task[ep_idx] = episode_tasks[ep_idx]
|
||||
elif new_task is not None:
|
||||
elif task_replacements and original_task in task_replacements:
|
||||
episode_to_task[ep_idx] = task_replacements[original_task]
|
||||
elif new_task:
|
||||
episode_to_task[ep_idx] = new_task
|
||||
else:
|
||||
elif original_task:
|
||||
# Keep original task if not overridden and no default provided
|
||||
original_tasks = dataset.meta.episodes[ep_idx]["tasks"]
|
||||
if not original_tasks:
|
||||
raise ValueError(f"Episode {ep_idx} has no tasks and no default task was provided")
|
||||
episode_to_task[ep_idx] = original_tasks[0]
|
||||
episode_to_task[ep_idx] = original_task
|
||||
else:
|
||||
raise ValueError(f"Episode {ep_idx} has no task; provide new_task or episode_tasks")
|
||||
|
||||
# Collect all unique tasks and create new task mapping
|
||||
unique_tasks = sorted(set(episode_to_task.values()))
|
||||
|
||||
@@ -386,6 +386,9 @@ class DatasetWriter:
|
||||
self._episodes_since_last_encoding = 0
|
||||
|
||||
if episode_data is None:
|
||||
# Post-save cleanup deliberately does not go through clear_episode_buffer():
|
||||
# staging frames of video cameras must survive here — the (possibly batched)
|
||||
# encoder still needs them and deletes them once each video is written.
|
||||
if len(self._meta.image_keys) > 0:
|
||||
self._delete_camera_frame_dirs(self._meta.image_keys)
|
||||
self.episode_buffer = self._create_episode_buffer()
|
||||
|
||||
@@ -17,8 +17,8 @@ from collections.abc import Sequence
|
||||
from typing import Any
|
||||
|
||||
from lerobot.configs import PipelineFeatureType
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.processor import DataProcessorPipeline
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION, OBS_IMAGES, OBS_STATE, OBS_STR
|
||||
from lerobot.utils.feature_utils import hw_to_dataset_features
|
||||
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
from collections import deque
|
||||
from collections.abc import Callable, Generator, Iterable, Iterator
|
||||
from pathlib import Path
|
||||
from typing import Literal
|
||||
|
||||
import datasets
|
||||
import numpy as np
|
||||
@@ -58,6 +59,10 @@ class LookAheadError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class _ShardExhaustedError(Exception):
|
||||
"""Raised when a streaming dataset shard has no more items."""
|
||||
|
||||
|
||||
class Backtrackable[T]:
|
||||
"""
|
||||
Wrap any iterator/iterable so you can step back up to `history` items
|
||||
@@ -178,7 +183,7 @@ class Backtrackable[T]:
|
||||
"""
|
||||
Check if we can go back `steps` items without raising an IndexError.
|
||||
"""
|
||||
return steps <= len(self._back_buf) + self._cursor
|
||||
return steps < len(self._back_buf) + self._cursor
|
||||
|
||||
def can_peek_ahead(self, steps: int = 1) -> bool:
|
||||
"""
|
||||
@@ -257,15 +262,16 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
return_uint8: bool = False,
|
||||
depth_output_unit: str = DEFAULT_DEPTH_UNIT,
|
||||
*,
|
||||
repo_type: Literal["dataset", "bucket"] = "dataset",
|
||||
token: str | bool | None = None,
|
||||
):
|
||||
"""Initialize a StreamingLeRobotDataset.
|
||||
|
||||
Args:
|
||||
repo_id (str): This is the repo id that will be used to fetch the dataset.
|
||||
root (Path | None, optional): Local directory to use for local datasets. When omitted, Hub
|
||||
metadata is resolved through a revision-safe snapshot cache under
|
||||
``$HF_LEROBOT_HOME/hub``.
|
||||
root (Path | None, optional): Local directory to use for local datasets. In bucket mode,
|
||||
this is an optional local metadata-cache directory; parquet and video data remain remote.
|
||||
When omitted, Hub metadata is resolved through the cache under ``$HF_LEROBOT_HOME/hub``.
|
||||
episodes (list[int] | None, optional): If specified, this will only load episodes specified by
|
||||
their episode_index in this list.
|
||||
image_transforms (Callable | None, optional): Transform to apply to image data.
|
||||
@@ -280,6 +286,8 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
shuffle (bool, optional): Whether to shuffle the dataset across exhaustions. Defaults to True.
|
||||
depth_output_unit (str, optional): Physical unit depth maps are dequantized to ("m" or "mm").
|
||||
Defaults to "mm".
|
||||
repo_type: "dataset" (default) or "bucket" to stream from an HF Storage Bucket
|
||||
over ``hf://buckets/``.
|
||||
token: Authentication token used while streaming this dataset from
|
||||
the Hub. Pass a string token, ``True`` to require the locally
|
||||
stored token, ``False`` to disable authentication, or ``None``
|
||||
@@ -287,10 +295,14 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
on the dataset instance after initialization.
|
||||
"""
|
||||
super().__init__()
|
||||
if repo_type not in ("dataset", "bucket"):
|
||||
raise ValueError(f"repo_type must be 'dataset' or 'bucket', got {repo_type!r}")
|
||||
|
||||
self.repo_id = repo_id
|
||||
self._requested_root = Path(root) if root else None
|
||||
self.repo_type = repo_type
|
||||
self._requested_root = Path(root) if root is not None else None
|
||||
self.root = self._requested_root if self._requested_root is not None else HF_LEROBOT_HOME / repo_id
|
||||
self.streaming_from_local = root is not None
|
||||
self.streaming_from_local = root is not None and self.repo_type == "dataset"
|
||||
|
||||
self.image_transforms = image_transforms
|
||||
self.episodes = episodes
|
||||
@@ -317,6 +329,7 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
self._requested_root,
|
||||
self.revision,
|
||||
force_cache_sync=force_cache_sync,
|
||||
repo_type=self.repo_type,
|
||||
token=token,
|
||||
)
|
||||
self.root = self.meta.root
|
||||
@@ -345,15 +358,26 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
self.delta_timestamps = delta_timestamps
|
||||
self.delta_indices = get_delta_indices(self.delta_timestamps, self.fps)
|
||||
|
||||
token_kwargs = {} if token is None or self.streaming_from_local else {"token": token}
|
||||
self.hf_dataset: datasets.IterableDataset = load_dataset(
|
||||
self.repo_id if not self.streaming_from_local else str(self.root),
|
||||
split="train",
|
||||
streaming=self.streaming,
|
||||
data_files="data/*/*.parquet",
|
||||
revision=self.revision,
|
||||
**token_kwargs,
|
||||
)
|
||||
token_kwargs = {} if token is None else {"token": token}
|
||||
if self.repo_type == "bucket":
|
||||
self.hf_dataset: datasets.IterableDataset = load_dataset(
|
||||
"parquet",
|
||||
data_files=f"hf://buckets/{self.repo_id}/data/*/*.parquet",
|
||||
split="train",
|
||||
streaming=self.streaming,
|
||||
**token_kwargs,
|
||||
)
|
||||
else:
|
||||
if self.streaming_from_local:
|
||||
token_kwargs = {}
|
||||
self.hf_dataset: datasets.IterableDataset = load_dataset(
|
||||
self.repo_id if not self.streaming_from_local else str(self.root),
|
||||
split="train",
|
||||
streaming=self.streaming,
|
||||
data_files="data/*/*.parquet",
|
||||
revision=self.revision,
|
||||
**token_kwargs,
|
||||
)
|
||||
|
||||
self.num_shards = min(self.hf_dataset.num_shards, max_num_shards)
|
||||
|
||||
@@ -422,10 +446,7 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
else:
|
||||
frames_buffer.append(frame)
|
||||
break # random shard sampled, switch shard
|
||||
except (
|
||||
RuntimeError,
|
||||
StopIteration,
|
||||
): # NOTE: StopIteration inside a generator throws a RuntimeError since python 3.7
|
||||
except _ShardExhaustedError:
|
||||
del idx_to_backtrack_dataset[shard_key] # Remove exhausted shard, onto another shard
|
||||
|
||||
# Once shards are all exhausted, shuffle the buffer and yield the remaining frames
|
||||
@@ -503,7 +524,11 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
|
||||
def make_frame(self, dataset_iterator: Backtrackable) -> Generator:
|
||||
"""Makes a frame starting from a dataset iterator"""
|
||||
item = next(dataset_iterator)
|
||||
try:
|
||||
item = next(dataset_iterator)
|
||||
except StopIteration as e:
|
||||
# Translate exhaustion here, before PEP 479 turns it into an indistinguishable RuntimeError.
|
||||
raise _ShardExhaustedError from e
|
||||
item = item_to_torch(item)
|
||||
|
||||
updates = [] # list of "updates" to apply to the item retrieved from hf_dataset (w/o camera features)
|
||||
|
||||
@@ -26,7 +26,6 @@ import numpy as np
|
||||
import packaging.version
|
||||
import torch
|
||||
from huggingface_hub import DatasetCard, DatasetCardData, HfApi
|
||||
from huggingface_hub.errors import RevisionNotFoundError
|
||||
|
||||
from lerobot.utils.utils import flatten_dict, unflatten_dict
|
||||
|
||||
@@ -51,6 +50,17 @@ The dataset you requested ({repo_id}) is only available in {version} format.
|
||||
As we cannot ensure forward compatibility with it, please update your current version of lerobot.
|
||||
"""
|
||||
|
||||
MISSING_VERSION_TAG_MESSAGE = """
|
||||
Your dataset must be tagged with a codebase version.
|
||||
Assuming _version_ is the codebase_version value in the info.json, you can run this:
|
||||
```python
|
||||
from huggingface_hub import HfApi
|
||||
|
||||
hub_api = HfApi()
|
||||
hub_api.create_tag("{repo_id}", tag="_version_", repo_type="dataset")
|
||||
```
|
||||
"""
|
||||
|
||||
|
||||
class CompatibilityError(Exception): ...
|
||||
|
||||
@@ -368,7 +378,7 @@ def get_safe_version(
|
||||
str: The safe version string (e.g., "v1.2.3") to use as a revision.
|
||||
|
||||
Raises:
|
||||
RevisionNotFoundError: If the repo has no version tags.
|
||||
RuntimeError: If the repo has no version tags.
|
||||
BackwardCompatibilityError: If only older major versions are available.
|
||||
ForwardCompatibilityError: If only newer major versions are available.
|
||||
"""
|
||||
@@ -378,17 +388,7 @@ def get_safe_version(
|
||||
hub_versions = get_repo_versions(repo_id) if token is None else get_repo_versions(repo_id, token=token)
|
||||
|
||||
if not hub_versions:
|
||||
raise RevisionNotFoundError(
|
||||
f"""Your dataset must be tagged with a codebase version.
|
||||
Assuming _version_ is the codebase_version value in the info.json, you can run this:
|
||||
```python
|
||||
from huggingface_hub import HfApi
|
||||
|
||||
hub_api = HfApi()
|
||||
hub_api.create_tag("{repo_id}", tag="_version_", repo_type="dataset")
|
||||
```
|
||||
"""
|
||||
)
|
||||
raise RuntimeError(MISSING_VERSION_TAG_MESSAGE.format(repo_id=repo_id))
|
||||
|
||||
if target_version in hub_versions:
|
||||
return f"v{target_version}"
|
||||
|
||||
@@ -507,7 +507,7 @@ class MetaworldEnv(EnvConfig):
|
||||
class RoboCasaEnv(EnvConfig):
|
||||
task: str = "CloseFridge"
|
||||
fps: int = 20
|
||||
episode_length: int = 1000
|
||||
episode_length: int | None = None
|
||||
obs_type: str = "pixels_agent_pos"
|
||||
render_mode: str = "rgb_array"
|
||||
camera_name: str = "robot0_agentview_left,robot0_eye_in_hand,robot0_agentview_right"
|
||||
|
||||
@@ -30,7 +30,7 @@ from gymnasium import spaces
|
||||
from libero.libero import benchmark, get_libero_path
|
||||
from libero.libero.envs import OffScreenRenderEnv
|
||||
|
||||
from lerobot.types import RobotObservation
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv, parse_camera_names
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ import metaworld.policies as policies
|
||||
import numpy as np
|
||||
from gymnasium import spaces
|
||||
|
||||
from lerobot.types import RobotObservation
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ import gymnasium as gym
|
||||
import numpy as np
|
||||
from gymnasium import spaces
|
||||
|
||||
from lerobot.types import RobotObservation
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv, parse_camera_names
|
||||
|
||||
@@ -98,6 +98,19 @@ def _resolve_tasks(task: str) -> tuple[list[str], str | None]:
|
||||
return names, None
|
||||
|
||||
|
||||
def _get_task_horizon(task: str) -> int:
|
||||
"""Return the rollout horizon registered by RoboCasa for a task."""
|
||||
from robocasa.utils.dataset_registry_utils import get_task_horizon
|
||||
|
||||
try:
|
||||
return int(get_task_horizon(task))
|
||||
except ValueError as exc:
|
||||
raise ValueError(
|
||||
f"No RoboCasa horizon is registered for task '{task}'. "
|
||||
"Set `--env.episode_length=<steps>` explicitly."
|
||||
) from exc
|
||||
|
||||
|
||||
def convert_action(flat_action: np.ndarray) -> dict[str, Any]:
|
||||
"""Split a flat (12,) action vector into a RoboCasa action dict.
|
||||
|
||||
@@ -154,7 +167,7 @@ class RoboCasaEnv(gym.Env):
|
||||
|
||||
self.camera_name = parse_camera_names(camera_name)
|
||||
|
||||
self._max_episode_steps = episode_length if episode_length is not None else 1000
|
||||
self._max_episode_steps = episode_length if episode_length is not None else _get_task_horizon(task)
|
||||
|
||||
# Deferred — created on first reset() inside the worker subprocess
|
||||
# to avoid inheriting stale GPU/EGL contexts across fork().
|
||||
|
||||
@@ -28,7 +28,7 @@ import numpy as np
|
||||
import torch
|
||||
from gymnasium import spaces
|
||||
|
||||
from lerobot.types import RobotObservation
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
from lerobot.utils.import_utils import _scipy_available
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv
|
||||
|
||||
@@ -37,7 +37,7 @@ import numpy as np
|
||||
from gymnasium import spaces
|
||||
from scipy.spatial.transform import Rotation
|
||||
|
||||
from lerobot.types import RobotObservation
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv
|
||||
|
||||
|
||||
@@ -22,6 +22,7 @@ from typing import TYPE_CHECKING, Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs.types import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import TransitionKey
|
||||
from lerobot.processor import (
|
||||
ComplementaryDataProcessorStep,
|
||||
PolicyAction,
|
||||
@@ -31,7 +32,6 @@ from lerobot.processor import (
|
||||
make_default_policy_processor_steps,
|
||||
make_policy_processor_pipelines,
|
||||
)
|
||||
from lerobot.types import TransitionKey
|
||||
from lerobot.utils.constants import OBS_STATE
|
||||
from lerobot.utils.import_utils import _transformers_available, require_package
|
||||
|
||||
|
||||
@@ -42,6 +42,9 @@ class Evo1Policy(PreTrainedPolicy):
|
||||
config_class = Evo1Config
|
||||
name = "evo1"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(self, config: Evo1Config, *, vlm_hub_kwargs: dict | None = None, **kwargs):
|
||||
super().__init__(config)
|
||||
config.validate_features()
|
||||
|
||||
@@ -21,6 +21,7 @@ from typing import Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AddBatchDimensionProcessorStep,
|
||||
DeviceProcessorStep,
|
||||
@@ -40,7 +41,6 @@ from lerobot.processor.converters import (
|
||||
policy_action_to_transition,
|
||||
transition_to_policy_action,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
ACTION,
|
||||
DONE,
|
||||
|
||||
@@ -28,6 +28,7 @@ if TYPE_CHECKING:
|
||||
|
||||
from lerobot.configs import FeatureType, PreTrainedConfig
|
||||
from lerobot.envs import EnvConfig, env_to_policy_features
|
||||
from lerobot.lerobot_types import PolicyAction
|
||||
from lerobot.processor import (
|
||||
AbsoluteActionsProcessorStep,
|
||||
PolicyProcessorPipeline,
|
||||
@@ -37,7 +38,6 @@ from lerobot.processor import (
|
||||
transition_to_batch,
|
||||
transition_to_policy_action,
|
||||
)
|
||||
from lerobot.types import PolicyAction
|
||||
from lerobot.utils.constants import (
|
||||
ACTION,
|
||||
POLICY_POSTPROCESSOR_DEFAULT_NAME,
|
||||
|
||||
@@ -68,6 +68,9 @@ class GrootPolicy(PreTrainedPolicy):
|
||||
name = "groot"
|
||||
config_class = GrootConfig
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(self, config: GrootConfig, **kwargs):
|
||||
"""Initialize Groot policy wrapper."""
|
||||
require_package("transformers", extra="groot")
|
||||
|
||||
@@ -50,6 +50,7 @@ if TYPE_CHECKING or _datasets_available:
|
||||
else:
|
||||
LeRobotDataset = None
|
||||
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AbsoluteActionsProcessorStep,
|
||||
AddBatchDimensionProcessorStep,
|
||||
@@ -66,7 +67,6 @@ from lerobot.processor import (
|
||||
transition_to_batch,
|
||||
transition_to_policy_action,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
ACTION,
|
||||
OBS_IMAGE,
|
||||
|
||||
@@ -520,6 +520,9 @@ class MolmoAct2Policy(PreTrainedPolicy):
|
||||
config_class = MolmoAct2Config
|
||||
name = "molmoact2"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return self.config.inference_action_mode == "continuous"
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: MolmoAct2Config,
|
||||
|
||||
@@ -1801,7 +1801,7 @@ class MolmoAct2VisionBackbone(nn.Module):
|
||||
valid = pooled_patches_idx >= 0
|
||||
valid_token = torch.any(valid, -1)
|
||||
|
||||
# Use `pooled_patches_idx` to arange the features for image pooling
|
||||
# Use `pooled_patches_idx` to arrange the features for image pooling
|
||||
batch_idx = torch.arange(
|
||||
pooled_patches_idx.shape[0],
|
||||
dtype=torch.long,
|
||||
|
||||
@@ -36,6 +36,7 @@ import torch
|
||||
from torch import Tensor
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AddBatchDimensionProcessorStep,
|
||||
DeviceProcessorStep,
|
||||
@@ -49,7 +50,6 @@ from lerobot.processor import (
|
||||
policy_action_to_transition,
|
||||
transition_to_policy_action,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
ACTION,
|
||||
OBS_IMAGES,
|
||||
|
||||
@@ -749,6 +749,9 @@ class PI0Policy(PreTrainedPolicy):
|
||||
config_class = PI0Config
|
||||
name = "pi0"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: PI0Config,
|
||||
|
||||
@@ -714,6 +714,9 @@ class PI05Policy(PreTrainedPolicy):
|
||||
config_class = PI05Config
|
||||
name = "pi05"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: PI05Config,
|
||||
|
||||
@@ -22,6 +22,7 @@ import numpy as np
|
||||
import torch
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AbsoluteActionsProcessorStep,
|
||||
PolicyAction,
|
||||
@@ -33,7 +34,6 @@ from lerobot.processor import (
|
||||
make_default_policy_processor_steps,
|
||||
make_policy_processor_pipelines,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import OBS_STATE
|
||||
|
||||
from .configuration_pi05 import PI05Config
|
||||
|
||||
@@ -22,6 +22,7 @@ import numpy as np
|
||||
import torch
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AbsoluteActionsProcessorStep,
|
||||
ActionTokenizerProcessorStep,
|
||||
@@ -34,7 +35,6 @@ from lerobot.processor import (
|
||||
make_default_policy_processor_steps,
|
||||
make_policy_processor_pipelines,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import OBS_STATE
|
||||
|
||||
from .configuration_pi0_fast import PI0FastConfig
|
||||
|
||||
@@ -249,6 +249,10 @@ class PreTrainedPolicy(nn.Module, HubMixin, abc.ABC):
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
"""Whether this policy implements Real-Time Chunking inference semantics."""
|
||||
return False
|
||||
|
||||
# TODO(aliberts, rcadene): split into 'forward' and 'compute_loss'?
|
||||
@abc.abstractmethod
|
||||
def forward(self, batch: dict[str, Tensor]) -> tuple[Tensor, dict | None]:
|
||||
|
||||
@@ -145,6 +145,9 @@ class SmolVLAPolicy(PreTrainedPolicy):
|
||||
config_class = SmolVLAConfig
|
||||
name = "smolvla"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: SmolVLAConfig,
|
||||
|
||||
@@ -168,14 +168,23 @@ class SmolVLMWithExpertModel(nn.Module):
|
||||
last_layers.append(self.num_vlm_layers - 2)
|
||||
frozen_layers = [
|
||||
"lm_head",
|
||||
"text_model.model.norm.weight",
|
||||
"text_model.norm.weight",
|
||||
]
|
||||
for layer in last_layers:
|
||||
frozen_layers.append(f"text_model.model.layers.{layer}.")
|
||||
frozen_layers.append(f"text_model.layers.{layer}.")
|
||||
|
||||
unmatched_patterns = set(frozen_layers)
|
||||
for name, params in self.vlm.named_parameters():
|
||||
if any(k in name for k in frozen_layers):
|
||||
matched_patterns = [k for k in frozen_layers if k in name]
|
||||
if matched_patterns:
|
||||
params.requires_grad = False
|
||||
unmatched_patterns.difference_update(matched_patterns)
|
||||
if unmatched_patterns:
|
||||
raise RuntimeError(
|
||||
"Some frozen layer patterns matched no VLM parameters, so the corresponding layers "
|
||||
"would silently remain trainable (parameter naming may have changed in transformers): "
|
||||
f"{sorted(unmatched_patterns)}"
|
||||
)
|
||||
# To avoid unused params issue with distributed training
|
||||
for name, params in self.lm_expert.named_parameters():
|
||||
if "lm_head" in name:
|
||||
|
||||
@@ -22,7 +22,7 @@ import torch
|
||||
from torch import nn
|
||||
|
||||
from lerobot.configs import FeatureType, PolicyFeature, PreTrainedConfig
|
||||
from lerobot.types import PolicyAction, RobotAction, RobotObservation
|
||||
from lerobot.lerobot_types import PolicyAction, RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION, OBS_STR
|
||||
from lerobot.utils.feature_utils import build_dataset_frame
|
||||
|
||||
|
||||
@@ -15,11 +15,13 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from lerobot.configs.policies import PreTrainedConfig
|
||||
from lerobot.configs.types import NormalizationMode
|
||||
from lerobot.configs.types import FeatureType, NormalizationMode, PolicyFeature
|
||||
from lerobot.optim.optimizers import AdamWConfig
|
||||
from lerobot.optim.schedulers import CosineDecayWithWarmupSchedulerConfig
|
||||
from lerobot.utils.constants import OBS_STATE
|
||||
|
||||
|
||||
@PreTrainedConfig.register_subclass("vla_jepa")
|
||||
@@ -122,6 +124,13 @@ class VLAJEPAConfig(PreTrainedConfig):
|
||||
if self.robot_state_feature is not None:
|
||||
self.state_dim = self.robot_state_feature.shape[0]
|
||||
|
||||
def set_dataset_feature_metadata(self, dataset_features: dict[str, Any]) -> None:
|
||||
"""Add `observation.state` to `input_features` if missing, so it gets normalized."""
|
||||
if OBS_STATE in self.input_features or OBS_STATE not in dataset_features:
|
||||
return
|
||||
shape = tuple(dataset_features[OBS_STATE]["shape"])
|
||||
self.input_features[OBS_STATE] = PolicyFeature(type=FeatureType.STATE, shape=shape)
|
||||
|
||||
def get_optimizer_preset(self) -> AdamWConfig:
|
||||
return AdamWConfig(
|
||||
lr=self.optimizer_lr,
|
||||
|
||||
@@ -16,6 +16,7 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from collections import deque
|
||||
from contextlib import nullcontext
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
@@ -26,6 +27,7 @@ from torch import Tensor, nn
|
||||
from lerobot.policies.pretrained import PreTrainedPolicy, T
|
||||
from lerobot.policies.utils import populate_queues
|
||||
from lerobot.utils.constants import ACTION, OBS_STATE
|
||||
from lerobot.utils.device_utils import is_amp_available
|
||||
from lerobot.utils.import_utils import _transformers_available, require_package
|
||||
|
||||
if TYPE_CHECKING or _transformers_available:
|
||||
@@ -39,6 +41,21 @@ from .configuration_vla_jepa import VLAJEPAConfig
|
||||
from .qwen_interface import Qwen3VLInterface
|
||||
from .world_model import ActionConditionedVideoPredictor
|
||||
|
||||
|
||||
def _get_autocast_context(device_type: str, dtype: torch.dtype = torch.bfloat16):
|
||||
"""Return an autocast context appropriate for the device.
|
||||
|
||||
MPS does not support ``torch.autocast`` at all. On CUDA devices
|
||||
without bfloat16 support (compute capability < 8.0) we fall back to
|
||||
float16.
|
||||
"""
|
||||
if not is_amp_available(device_type):
|
||||
return nullcontext()
|
||||
if device_type == "cuda" and dtype == torch.bfloat16 and not torch.cuda.is_bf16_supported():
|
||||
dtype = torch.float16
|
||||
return torch.autocast(device_type=device_type, dtype=dtype)
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# Native VLA-JEPA Model - follows original starVLA VLA_JEPA.py implementation
|
||||
# ============================================================================
|
||||
@@ -183,7 +200,7 @@ class VLAJEPAModel(nn.Module):
|
||||
action_idx = action_mask.nonzero(as_tuple=True)
|
||||
|
||||
device_type = next(self.parameters()).device.type
|
||||
with torch.autocast(device_type=device_type, dtype=torch.bfloat16):
|
||||
with _get_autocast_context(device_type, torch.bfloat16):
|
||||
last_hidden = self._qwen_last_decoder_hidden(qwen_inputs) # [B, seq_len, H]
|
||||
b, _, h = last_hidden.shape
|
||||
embodied_action_tokens = last_hidden[embodied_idx[0], embodied_idx[1], :].view(b, -1, h)
|
||||
@@ -250,7 +267,7 @@ class VLAJEPAModel(nn.Module):
|
||||
) -> Tensor:
|
||||
"""Flow-matching action-head loss, repeated over `repeated_diffusion_steps`."""
|
||||
device_type = next(self.parameters()).device.type
|
||||
with torch.autocast(device_type=device_type, dtype=torch.float32):
|
||||
with _get_autocast_context(device_type, torch.float32):
|
||||
r = self.config.repeated_diffusion_steps
|
||||
horizon = self.config.chunk_size
|
||||
actions_target = actions[:, -horizon:, :].to(torch.float32).repeat(r, 1, 1)
|
||||
@@ -399,7 +416,8 @@ class VLAJEPAPolicy(PreTrainedPolicy):
|
||||
state = batch.get(OBS_STATE)
|
||||
if state is not None:
|
||||
if state.ndim > 2:
|
||||
state = state[:, -1, :]
|
||||
# deltas are forward-looking here, so index 0 is the current observation, not -1.
|
||||
state = state[:, 0, :]
|
||||
inputs["state"] = (state.unsqueeze(1) if state.ndim == 2 else state).float() # [B, 1, dim]
|
||||
|
||||
return inputs
|
||||
|
||||
@@ -150,7 +150,7 @@ class XVLAModel(nn.Module):
|
||||
# Freeze or unfreeze policy transformer
|
||||
if not self.config.train_policy_transformer:
|
||||
for name, param in self.transformer.named_parameters():
|
||||
if "soft_prompts" not in name:
|
||||
if "soft_prompt" not in name:
|
||||
param.requires_grad = False
|
||||
|
||||
# Freeze or unfreeze soft prompts
|
||||
|
||||
@@ -21,6 +21,7 @@ import numpy as np
|
||||
import torch
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
ObservationProcessorStep,
|
||||
PolicyAction,
|
||||
@@ -31,7 +32,6 @@ from lerobot.processor import (
|
||||
make_default_policy_processor_steps,
|
||||
make_policy_processor_pipelines,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
IMAGENET_STATS,
|
||||
OBS_IMAGES,
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from lerobot.types import (
|
||||
from lerobot.lerobot_types import (
|
||||
EnvAction,
|
||||
EnvTransition,
|
||||
PolicyAction,
|
||||
|
||||
@@ -25,7 +25,7 @@ from dataclasses import dataclass, field
|
||||
from torch import Tensor
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvTransition, PolicyAction
|
||||
from lerobot.lerobot_types import EnvTransition, PolicyAction
|
||||
from lerobot.utils.constants import OBS_ENV_STATE, OBS_IMAGE, OBS_IMAGES, OBS_STATE
|
||||
|
||||
from .pipeline import (
|
||||
|
||||
@@ -23,7 +23,7 @@ from typing import Any
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from lerobot.types import EnvTransition, PolicyAction, RobotAction, RobotObservation, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, PolicyAction, RobotAction, RobotObservation, TransitionKey
|
||||
from lerobot.utils.constants import ACTION, DONE, INFO, OBS_PREFIX, REWARD, TRUNCATED
|
||||
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
from dataclasses import dataclass
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import PolicyAction, RobotAction
|
||||
from lerobot.lerobot_types import PolicyAction, RobotAction
|
||||
|
||||
from .pipeline import ActionProcessorStep, ProcessorStepRegistry, RobotActionProcessorStep
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ from typing import Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.utils.device_utils import get_safe_torch_device
|
||||
|
||||
from .pipeline import ProcessorStep, ProcessorStepRegistry
|
||||
|
||||
@@ -20,7 +20,7 @@ from typing import Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs.policies import PreTrainedConfig
|
||||
from lerobot.types import PolicyAction, RobotAction, RobotObservation
|
||||
from lerobot.lerobot_types import PolicyAction, RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import POLICY_POSTPROCESSOR_DEFAULT_NAME, POLICY_PREPROCESSOR_DEFAULT_NAME
|
||||
|
||||
from .batch_processor import AddBatchDimensionProcessorStep
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
from dataclasses import dataclass
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvAction, EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.lerobot_types import EnvAction, EnvTransition, PolicyAction, TransitionKey
|
||||
|
||||
from .converters import to_tensor
|
||||
from .hil_processor import TELEOP_ACTION_KEY
|
||||
|
||||
@@ -29,7 +29,7 @@ from lerobot.teleoperators.utils import TeleopEvents
|
||||
if TYPE_CHECKING:
|
||||
from lerobot.teleoperators.teleoperator import Teleoperator
|
||||
|
||||
from lerobot.types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
|
||||
from .pipeline import (
|
||||
ComplementaryDataProcessorStep,
|
||||
|
||||
@@ -25,7 +25,7 @@ import torch
|
||||
from torch import Tensor
|
||||
|
||||
from lerobot.configs import FeatureType, NormalizationMode, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
|
||||
@@ -44,8 +44,15 @@ import torch
|
||||
from huggingface_hub import hf_hub_download
|
||||
from safetensors.torch import load_file, save_file
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvAction, EnvTransition, PolicyAction, RobotAction, RobotObservation, TransitionKey
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import (
|
||||
EnvAction,
|
||||
EnvTransition,
|
||||
PolicyAction,
|
||||
RobotAction,
|
||||
RobotObservation,
|
||||
TransitionKey,
|
||||
)
|
||||
from lerobot.utils.constants import HF_LEROBOT_HOME
|
||||
from lerobot.utils.hub import HubMixin
|
||||
|
||||
@@ -866,6 +873,13 @@ class DataProcessorPipeline[TInput, TOutput](HubMixin):
|
||||
return json.load(f), Path(config_path).parent
|
||||
|
||||
except Exception as e:
|
||||
if cls._hub_model_requires_migration(model_id, hub_download_kwargs):
|
||||
revision = hub_download_kwargs.get("revision")
|
||||
cls._suggest_processor_migration(
|
||||
model_id,
|
||||
f"Config file '{config_filename}' not found on the Hugging Face Hub",
|
||||
revision=revision if isinstance(revision, str) else None,
|
||||
)
|
||||
raise FileNotFoundError(
|
||||
f"Could not find '{config_filename}' on the HuggingFace Hub at '{model_id}'"
|
||||
) from e
|
||||
@@ -1330,6 +1344,62 @@ class DataProcessorPipeline[TInput, TOutput](HubMixin):
|
||||
# Have JSON files but no processor configs - suggest migration
|
||||
return True
|
||||
|
||||
@classmethod
|
||||
def _hub_model_requires_migration(cls, model_id: str, hub_download_kwargs: dict[str, Any]) -> bool:
|
||||
"""Check whether a Hub repository contains a legacy LeRobot policy config.
|
||||
|
||||
A missing processor file is not sufficient evidence by itself: the repository
|
||||
may be private, unavailable, or unrelated to LeRobot. This method therefore
|
||||
fetches the policy's ``config.json`` and checks for the feature declarations
|
||||
that identify a LeRobot policy checkpoint. Any lookup or parsing failure is
|
||||
ignored so the original processor-file error remains visible.
|
||||
|
||||
Args:
|
||||
model_id: Hugging Face Hub model repository ID.
|
||||
hub_download_kwargs: Authentication, cache, and revision arguments used
|
||||
for the original processor lookup.
|
||||
|
||||
Returns:
|
||||
True when the repository has a legacy LeRobot policy configuration.
|
||||
"""
|
||||
try:
|
||||
config_path = hf_hub_download(
|
||||
repo_id=model_id,
|
||||
filename="config.json",
|
||||
repo_type="model",
|
||||
**hub_download_kwargs,
|
||||
)
|
||||
with open(config_path) as f:
|
||||
config = json.load(f)
|
||||
except Exception:
|
||||
# This is a best-effort diagnostic called while handling the original
|
||||
# processor lookup failure, which must remain the visible error.
|
||||
return False
|
||||
|
||||
feature_types = {feature_type.value for feature_type in FeatureType}
|
||||
|
||||
def is_policy_feature_mapping(features: Any) -> bool:
|
||||
return (
|
||||
isinstance(features, dict)
|
||||
and bool(features)
|
||||
and all(
|
||||
isinstance(name, str)
|
||||
and isinstance(feature, dict)
|
||||
and feature.get("type") in feature_types
|
||||
and isinstance(feature.get("shape"), list)
|
||||
and all(isinstance(dimension, int) for dimension in feature["shape"])
|
||||
for name, feature in features.items()
|
||||
)
|
||||
)
|
||||
|
||||
return (
|
||||
isinstance(config, dict)
|
||||
and isinstance(config.get("type"), str)
|
||||
and bool(config["type"])
|
||||
and is_policy_feature_mapping(config.get("input_features"))
|
||||
and is_policy_feature_mapping(config.get("output_features"))
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def _is_processor_config(cls, config: Any) -> bool:
|
||||
"""Check if config follows DataProcessorPipeline format.
|
||||
@@ -1403,7 +1473,13 @@ class DataProcessorPipeline[TInput, TOutput](HubMixin):
|
||||
return True
|
||||
|
||||
@classmethod
|
||||
def _suggest_processor_migration(cls, model_path: str | Path, original_error: str) -> None:
|
||||
def _suggest_processor_migration(
|
||||
cls,
|
||||
model_path: str | Path,
|
||||
original_error: str,
|
||||
*,
|
||||
revision: str | None = None,
|
||||
) -> None:
|
||||
"""Raise migration error when we detect JSON files but no processor configs.
|
||||
|
||||
This method is called when migration detection determines that a model
|
||||
@@ -1438,6 +1514,7 @@ class DataProcessorPipeline[TInput, TOutput](HubMixin):
|
||||
Args:
|
||||
model_path: Path to the model directory needing migration
|
||||
original_error: The error that triggered migration detection (for context)
|
||||
revision: Optional Hub revision containing the legacy checkpoint.
|
||||
|
||||
Raises:
|
||||
ProcessorMigrationError: Always raised (this method never returns normally)
|
||||
@@ -1445,6 +1522,8 @@ class DataProcessorPipeline[TInput, TOutput](HubMixin):
|
||||
migration_command = (
|
||||
f"python src/lerobot/processor/migrate_policy_normalization.py --pretrained-path {model_path}"
|
||||
)
|
||||
if revision is not None:
|
||||
migration_command += f" --revision {revision}"
|
||||
|
||||
raise ProcessorMigrationError(model_path, migration_command, original_error)
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ from typing import Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import PolicyAction, RobotAction
|
||||
from lerobot.lerobot_types import PolicyAction, RobotAction
|
||||
from lerobot.utils.constants import ACTION
|
||||
|
||||
from .pipeline import ActionProcessorStep, ProcessorStepRegistry
|
||||
|
||||
@@ -20,7 +20,7 @@ import torch
|
||||
from torch import Tensor
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import OBS_STATE
|
||||
|
||||
from .delta_action_processor import MapDeltaActionToRobotActionStep, MapTensorToDeltaActionDictStep
|
||||
|
||||
@@ -23,7 +23,7 @@ from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.configs.recipe import TrainingRecipe
|
||||
from lerobot.datasets.language import LANGUAGE_EVENTS, LANGUAGE_PERSISTENT
|
||||
from lerobot.datasets.language_render import render_sample
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.utils import unwrap_scalar
|
||||
|
||||
from .pipeline import ProcessorStep, ProcessorStepRegistry
|
||||
|
||||
@@ -30,7 +30,7 @@ from typing import TYPE_CHECKING, Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.types import EnvTransition, RobotObservation, TransitionKey
|
||||
from lerobot.lerobot_types import EnvTransition, RobotObservation, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
ACTION_TOKEN_MASK,
|
||||
ACTION_TOKENS,
|
||||
|
||||
@@ -57,10 +57,10 @@ import torch
|
||||
from tqdm import tqdm
|
||||
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
from lerobot.lerobot_types import TransitionKey
|
||||
from lerobot.rewards.robometer.configuration_robometer import RobometerConfig
|
||||
from lerobot.rewards.robometer.modeling_robometer import RobometerRewardModel
|
||||
from lerobot.rewards.robometer.processor_robometer import RobometerEncoderProcessorStep
|
||||
from lerobot.types import TransitionKey
|
||||
|
||||
DEFAULT_OUTPUT_FILENAME = "robometer_progress.parquet"
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user