mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-30 21:19:40 +00:00
Compare commits
8 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| ee3e796270 | |||
| e548375e4c | |||
| 17d5675738 | |||
| ffd0e26fbe | |||
| 9cade7db18 | |||
| 775bbc19f4 | |||
| 2b78c7e582 | |||
| b101ff0e56 |
+7
-11
@@ -61,20 +61,16 @@ Full details in [`docs/source/so101.mdx`](./docs/source/so101.mdx) and [`docs/so
|
||||
**4.1 Install**
|
||||
|
||||
```bash
|
||||
# uv (recommended — see AGENTS.md and CLAUDE.md)
|
||||
uv sync --locked --extra feetech # SO-100/SO-101 motor stack
|
||||
# uv sync --locked --extra all # everything
|
||||
# uv sync --locked --extra smolvla # add SmolVLA deps
|
||||
|
||||
# pip (alternative, e.g. when not working from source)
|
||||
# pip install 'lerobot[feetech]'
|
||||
# pip install 'lerobot[all]'
|
||||
# pip install 'lerobot[smolvla]'
|
||||
|
||||
pip install 'lerobot[feetech]' # SO-100/SO-101 motor stack
|
||||
# pip install 'lerobot[all]' # everything
|
||||
# pip install 'lerobot[aloha,pusht]' # specific features
|
||||
# pip install 'lerobot[smolvla]' # add SmolVLA deps
|
||||
git lfs install && git lfs pull
|
||||
hf auth login # required to push datasets/policies
|
||||
hf auth login # required to push datasets/policies
|
||||
```
|
||||
|
||||
Contributors can alternatively use `uv sync --locked --extra feetech` (see `AGENTS.md`).
|
||||
|
||||
**4.2 Find USB ports** — run once per arm, unplug when prompted.
|
||||
|
||||
```bash
|
||||
|
||||
@@ -68,16 +68,17 @@ ENV HOME=/home/user_lerobot \
|
||||
# issues with MuJoCo and OpenGL drivers.
|
||||
RUN uv venv --python python${PYTHON_VERSION}
|
||||
|
||||
# Install third-party dependencies separately for layer caching
|
||||
# Install Python dependencies for caching
|
||||
COPY --chown=user_lerobot:user_lerobot setup.py pyproject.toml uv.lock README.md MANIFEST.in ./
|
||||
RUN uv sync --locked --extra all --no-install-project --no-cache
|
||||
COPY --chown=user_lerobot:user_lerobot src/ src/
|
||||
|
||||
RUN uv sync --locked --extra all --no-cache
|
||||
|
||||
RUN chmod +x /lerobot/.venv/lib/python${PYTHON_VERSION}/site-packages/triton/backends/nvidia/bin/ptxas
|
||||
|
||||
# Copy the application source code and install the local project
|
||||
# Copy the rest of the application source code
|
||||
# Make sure to have the git-LFS files for testing
|
||||
COPY --chown=user_lerobot:user_lerobot . .
|
||||
RUN uv sync --locked --extra all --no-cache
|
||||
|
||||
# Set the default command
|
||||
CMD ["/bin/bash"]
|
||||
|
||||
@@ -60,14 +60,15 @@ ENV HOME=/home/user_lerobot \
|
||||
# run other Python projects in the same container without dependency conflicts.
|
||||
RUN uv venv
|
||||
|
||||
# Install third-party dependencies separately for layer caching
|
||||
# Install Python dependencies for caching
|
||||
COPY --chown=user_lerobot:user_lerobot setup.py pyproject.toml uv.lock README.md MANIFEST.in ./
|
||||
RUN uv sync --locked --extra all --no-install-project --no-cache
|
||||
COPY --chown=user_lerobot:user_lerobot src/ src/
|
||||
|
||||
# Copy the application code and install the local project
|
||||
RUN uv sync --locked --extra all --no-cache
|
||||
|
||||
# Copy the rest of the application code
|
||||
# Make sure to have the git-LFS files for testing
|
||||
COPY --chown=user_lerobot:user_lerobot . .
|
||||
RUN uv sync --locked --extra all --no-cache
|
||||
|
||||
# Set the default command
|
||||
CMD ["/bin/bash"]
|
||||
|
||||
@@ -58,7 +58,7 @@ final_action = postprocessor(action)
|
||||
|
||||
## Hardware API redesign
|
||||
|
||||
PR [#777](https://github.com/huggingface/lerobot/pull/777) improves the LeRobot calibration but is **not backward-compatible**. Below is an overview of what changed and how you can continue to work with datasets created before this pull request.
|
||||
PR [#777](https://github.com/huggingface/lerobot/pull/777) improves the LeRobot calibration but is **not backward-compatible**. Below is a overview of what changed and how you can continue to work with datasets created before this pull request.
|
||||
|
||||
### What changed?
|
||||
|
||||
@@ -129,8 +129,8 @@ python examples/backward_compatibility/replay.py \
|
||||
|
||||
Policies output actions in the same format as the datasets (`torch.Tensors`). Therefore, the same transformations should be applied.
|
||||
|
||||
To find these transformations, we recommend first replaying an episode of the dataset your policy was trained on using the section above.
|
||||
Then, add these same transformations to your inference script (shown here in the `record.py` script):
|
||||
To find these transformations, we recommend to first try and and replay an episode of the dataset your policy was trained on using the section above.
|
||||
Then, add these same transformations on your inference script (shown here in the `record.py` script):
|
||||
|
||||
```diff
|
||||
action_values = predict_action(
|
||||
|
||||
@@ -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`.
|
||||
|
||||
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.
|
||||
On the RealSense D405, the color stream is provided by the Stereo Module, so changing manual
|
||||
exposure or gain also affects the depth stream.
|
||||
|
||||
</hfoption>
|
||||
</hfoptions>
|
||||
|
||||
@@ -88,6 +88,20 @@ policy_preprocessor = NormalizerProcessorStep(stats=dataset_stats)
|
||||
|
||||
The same policy can work with different environment processors, and the same environment processor can work with different policies:
|
||||
|
||||
````python
|
||||
# Use SmolVLA policy with LIBERO environment
|
||||
# Use SmolVLA policy with LIBERO environment
|
||||
libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(
|
||||
env_cfg=libero_cfg,
|
||||
policy_cfg=smolvla_cfg,
|
||||
)
|
||||
smolvla_preprocessor, smolvla_postprocessor = make_pre_post_processors(smolvla_cfg)
|
||||
# Or use ACT policy with the same LIBERO environment
|
||||
libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(
|
||||
env_cfg=libero_cfg,
|
||||
policy_cfg=act_cfg,
|
||||
)
|
||||
act_preprocessor, act_postprocessor = make_pre_post_processors(act_cfg)
|
||||
```python
|
||||
# Use SmolVLA policy with LIBERO environment
|
||||
libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(
|
||||
@@ -102,7 +116,6 @@ libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(
|
||||
policy_cfg=act_cfg,
|
||||
)
|
||||
act_preprocessor, act_postprocessor = make_pre_post_processors(act_cfg)
|
||||
```
|
||||
|
||||
### 3. **Easier Experimentation**
|
||||
|
||||
@@ -132,7 +145,7 @@ class LiberoVelocityProcessorStep(ObservationProcessorStep):
|
||||
state = torch.cat([eef_pos, eef_axisangle, eef_vel,
|
||||
gripper_pos, gripper_vel], dim=-1) # 14D
|
||||
return state
|
||||
```
|
||||
````
|
||||
|
||||
### 4. **Cleaner Environment Code**
|
||||
|
||||
|
||||
@@ -40,10 +40,10 @@ This tutorial guides you through updating the firmware of Feetech motors using t
|
||||
For each motor you want to update:
|
||||
|
||||
1. **Select the motor** from the list by clicking on it
|
||||
2. **Click the Upgrade tab**:
|
||||
3. **Click the Online button**:
|
||||
- If a potential firmware update is found, it will be displayed in the box
|
||||
4. **Click the Upgrade button**:
|
||||
2. **Click on Upgrade tab**:
|
||||
3. **Click on Online button**:
|
||||
- If an potential firmware update is found, it will be displayed in the box
|
||||
4. **Click on Upgrade button**:
|
||||
- The update progress will be displayed
|
||||
|
||||
## Step 6: Verify Update
|
||||
|
||||
@@ -59,7 +59,6 @@ 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`.
|
||||
|
||||
@@ -211,7 +211,7 @@ Record, Replay and Train with Hope-JR is still experimental.
|
||||
|
||||
### Record
|
||||
|
||||
This step records the dataset, which can be seen as an example [here](https://huggingface.co/datasets/nepyope/hand_record_test_with_video_data).
|
||||
This step records the dataset, which can be seen as an example [here](https://huggingface.co/datasets/nepyope/hand_record_test_with_video_data/settings).
|
||||
|
||||
```bash
|
||||
lerobot-record \
|
||||
|
||||
+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.
|
||||
|
||||
@@ -18,7 +18,7 @@ If you're using Feetech or Dynamixel motors, LeRobot provides built-in bus inter
|
||||
- [`DynamixelMotorsBus`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/motors/dynamixel/dynamixel.py) – for controlling Dynamixel servos
|
||||
|
||||
Please refer to the [`MotorsBus`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/motors/motors_bus.py) abstract class to learn about its API.
|
||||
For a good example of how it can be used, you can have a look at our own [SO101 follower implementation](https://github.com/huggingface/lerobot/blob/main/src/lerobot/robots/so_follower/so_follower.py)
|
||||
For a good example of how it can be used, you can have a look at our own [SO101 follower implementation](https://github.com/huggingface/lerobot/blob/main/src/lerobot/robots/so_follower/so101_follower/so101_follower.py)
|
||||
|
||||
Use these if compatible. Otherwise, you'll need to find or write a Python interface (not covered in this tutorial):
|
||||
|
||||
|
||||
@@ -51,7 +51,7 @@ In addition to these instructions, you need to install the Feetech SDK & ZeroMQ
|
||||
pip install -e ".[lekiwi]"
|
||||
```
|
||||
|
||||
Great 🤗! You are now done installing LeRobot, and we can begin assembling the SO100/SO101 arms and the mobile base 🤖.
|
||||
Great :hugs:! You are now done installing LeRobot, and we can begin assembling the SO100/SO101 arms and the mobile base :robot:.
|
||||
Every time you now want to use LeRobot, you can go to the `~/lerobot` folder where we installed LeRobot and run one of the commands.
|
||||
|
||||
# Step-by-Step Assembly Instructions
|
||||
|
||||
@@ -174,7 +174,7 @@ The model takes images, text instructions, and robot state as input, and outputs
|
||||
|
||||
## Reproducing π₀Fast results
|
||||
|
||||
We reproduce the results of π₀Fast on the LIBERO benchmark using the LeRobot implementation. We take the LeRobot PiFast base model [lerobot/pi0fast-base](https://huggingface.co/lerobot/pi0fast-base) and finetune for an additional 40k steps in bfloat16, with batch size of 256 on 8 H100 GPUs using the [HuggingFace LIBERO dataset](https://huggingface.co/datasets/HuggingFaceVLA/libero).
|
||||
We reproduce the results of π₀Fast on the LIBERO benchmark using the LeRobot implementation. We take the LeRobot PiFast base model [lerobot/pi0fast-base](https://huggingface.co/lerobot/pi0fast-base) and finetune for an additional 40kk steps in bfloat16, with batch size of 256 on 8 H100 GPUs using the [HuggingFace LIBERO dataset](https://huggingface.co/datasets/HuggingFaceVLA/libero).
|
||||
|
||||
The finetuned model can be found here:
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ With processors, you choose the learning features you want to use for your polic
|
||||
## Three pipelines
|
||||
|
||||
We often compose three pipelines. Depending on your setup, some can be empty if action and observation spaces already match.
|
||||
Each of these pipelines handles different conversions between different action and observation spaces. Below is a quick explanation of each pipeline.
|
||||
Each of these pipelines handle different conversions between different action and observation spaces. Below is a quick explanation of each pipeline.
|
||||
|
||||
1. Pipeline 1: Teleop action space → dataset action space (phone pose → EE targets)
|
||||
2. Pipeline 2: Dataset action space → robot command space (EE targets → joints)
|
||||
@@ -74,15 +74,15 @@ In the phone to SO-100 follower examples we use the following adapters:
|
||||
- `robot_action_to_transition`: transforms the teleop action dict to a pipeline transition.
|
||||
- `transition_to_robot_action`: transforms the pipeline transition to a robot action dict.
|
||||
- `observation_to_transition`: transforms the robot observation dict to a pipeline transition.
|
||||
- `transition_to_observation`: transforms the pipeline transition to an observation dict.
|
||||
- `transition_to_observation`: transforms the pipeline transition to a observation dict.
|
||||
|
||||
Check out [src/lerobot/processor/converters.py](https://github.com/huggingface/lerobot/blob/main/src/lerobot/processor/converters.py) for more details.
|
||||
Checkout [src/lerobot/processor/converters.py](https://github.com/huggingface/lerobot/blob/main/src/lerobot/processor/converters.py) for more details.
|
||||
|
||||
## Dataset feature contracts
|
||||
|
||||
Dataset features are determined by the keys saved in the dataset. Each step can declare what features it modifies in a contract called `transform_features(...)`. Once you build a processor, the processor can then aggregate all of these features with `aggregate_pipeline_dataset_features()` and merge multiple feature dicts with `combine_feature_dicts(...)`.
|
||||
|
||||
Below is an example of how we declare features with the `transform_features` method in the phone to SO-100 follower examples:
|
||||
Below is and example of how we declare features with the `transform_features` method in the phone to SO-100 follower examples:
|
||||
|
||||
```python
|
||||
def transform_features(
|
||||
|
||||
@@ -82,8 +82,6 @@ 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
|
||||
|
||||
+2
-2
@@ -57,7 +57,7 @@ policy_cfg.rtc_config = RTCConfig(
|
||||
policy = PI0Policy.from_pretrained("lerobot/pi0_base", policy_cfg=policy_cfg, device="cuda")
|
||||
|
||||
# Now use predict_action_chunk with RTC parameters
|
||||
inference_delay = 4 # How many steps of inference latency, this value should be calculated based on the inference latency of the policy
|
||||
inference_delay = 4 # How many steps of inference latency, this values should be calculated based on the inference latency of the policy
|
||||
|
||||
# Initialize the action queue
|
||||
action_queue = ActionQueue(policy_cfg.rtc_config)
|
||||
@@ -100,7 +100,7 @@ Typical values: 8-12 steps
|
||||
RTCConfig(execution_horizon=10)
|
||||
```
|
||||
|
||||
**`max_guidance_weight`**: How strongly to enforce consistency with the previous chunk. This is a hyperparameter that can be tuned to balance the smoothness of the transitions and the reactivity of the policy. For 10 steps flow matching (SmolVLA, Pi0, Pi0.5), a value of 10.0 is an optimal value.
|
||||
**`max_guidance_weight`**: How strongly to enforce consistency with the previous chunk. This is a hyperparameter that can be tuned to balance the smoothness of the transitions and the reactivity of the policy. For 10 steps flow matching (SmolVLA, Pi0, Pi0.5), a value of 10.0 is a optimal value.
|
||||
|
||||
**`prefix_attention_schedule`**: How to weight consistency across the overlap region.
|
||||
|
||||
|
||||
@@ -93,7 +93,7 @@ lerobot-train --help
|
||||
|
||||
## Evaluate the finetuned model and run it in real-time
|
||||
|
||||
Similarly for when recording an episode, it is recommended that you are logged in to the HuggingFace Hub. You can follow the corresponding steps: [Record a dataset](./il_robots#record-a-dataset).
|
||||
Similarly for when recording an episode, it is recommended that you are logged in to the HuggingFace Hub. You can follow the corresponding steps: [Record a dataset](./il_robots).
|
||||
Once you are logged in, you can run inference in your setup by doing:
|
||||
|
||||
```bash
|
||||
|
||||
@@ -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 the leader holder using 1 M2x6mm screw.
|
||||
- Attach the handle to motor 5 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.
|
||||
|
||||
|
||||
@@ -50,11 +50,11 @@ lerobot-edit-dataset \
|
||||
Divide a dataset into multiple subsets.
|
||||
|
||||
```bash
|
||||
# Split by fractions (e.g. 60% train, 20% val, 20% test)
|
||||
# Split by fractions (e.g. 80% train, 20% test, 20% val)
|
||||
lerobot-edit-dataset \
|
||||
--repo_id lerobot/pusht \
|
||||
--operation.type split \
|
||||
--operation.splits '{"train": 0.6, "val": 0.2, "test": 0.2}'
|
||||
--operation.splits '{"train": 0.8, "test": 0.2, "val": 0.2}'
|
||||
|
||||
# Split by specific episode indices
|
||||
lerobot-edit-dataset \
|
||||
|
||||
@@ -44,7 +44,6 @@ 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,
|
||||
@@ -57,6 +56,7 @@ 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.lerobot_types import RobotAction
|
||||
from 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.lerobot_types import RobotAction
|
||||
from 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
|
||||
|
||||
@@ -21,7 +21,6 @@ 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
|
||||
@@ -39,6 +38,7 @@ 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
|
||||
|
||||
@@ -16,7 +16,6 @@
|
||||
|
||||
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,
|
||||
@@ -37,6 +36,7 @@ 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
|
||||
|
||||
@@ -17,7 +17,6 @@
|
||||
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,
|
||||
@@ -28,6 +27,7 @@ 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
|
||||
|
||||
@@ -27,7 +27,6 @@ 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,
|
||||
@@ -44,6 +43,7 @@ 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
|
||||
|
||||
|
||||
@@ -15,7 +15,6 @@
|
||||
|
||||
import time
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -32,6 +31,7 @@ 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
|
||||
|
||||
|
||||
@@ -21,7 +21,6 @@ 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
|
||||
@@ -39,6 +38,7 @@ 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
|
||||
|
||||
@@ -17,7 +17,6 @@
|
||||
|
||||
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,
|
||||
@@ -34,6 +33,7 @@ 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
|
||||
|
||||
@@ -18,7 +18,6 @@
|
||||
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,
|
||||
@@ -29,6 +28,7 @@ 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
|
||||
|
||||
@@ -25,7 +25,6 @@ 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,
|
||||
@@ -42,6 +41,7 @@ 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
|
||||
|
||||
|
||||
@@ -16,7 +16,6 @@
|
||||
|
||||
import time
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.model.kinematics import RobotKinematics
|
||||
from lerobot.processor import (
|
||||
RobotProcessorPipeline,
|
||||
@@ -31,6 +30,7 @@ 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
|
||||
|
||||
|
||||
+1
-14
@@ -67,7 +67,7 @@ dependencies = [
|
||||
"einops>=0.8.0,<0.9.0",
|
||||
|
||||
# Config & Hub
|
||||
"draccus>=0.11.6,<0.12.0",
|
||||
"draccus==0.10.0", # TODO: Relax version constraint
|
||||
"huggingface-hub>=1.0.0,<2.0.0",
|
||||
"requests>=2.32.0,<3.0.0",
|
||||
|
||||
@@ -494,19 +494,6 @@ ignore_errors = true
|
||||
module = "lerobot.envs.*"
|
||||
ignore_errors = false
|
||||
|
||||
[[tool.mypy.overrides]]
|
||||
module = "lerobot.annotations.*"
|
||||
ignore_errors = false
|
||||
disallow_untyped_defs = true
|
||||
disallow_incomplete_defs = true
|
||||
check_untyped_defs = true
|
||||
|
||||
[[tool.mypy.overrides]]
|
||||
module = "lerobot.transforms.*"
|
||||
ignore_errors = false
|
||||
disallow_untyped_defs = true
|
||||
disallow_incomplete_defs = true
|
||||
check_untyped_defs = true
|
||||
|
||||
# [[tool.mypy.overrides]]
|
||||
# module = "lerobot.utils.*"
|
||||
|
||||
@@ -38,7 +38,6 @@ 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 (
|
||||
@@ -46,6 +45,7 @@ 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
|
||||
|
||||
@@ -365,12 +365,11 @@ class RealSenseCamera(Camera):
|
||||
return self._async_read(timeout_ms=10000, read_depth=read_depth)
|
||||
|
||||
def _get_color_sensor(self) -> "rs.sensor":
|
||||
"""Returns the dedicated "RGB Camera" sensor that controls the color stream.
|
||||
"""Returns the sensor that controls the color stream.
|
||||
|
||||
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.
|
||||
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.
|
||||
"""
|
||||
if self.rs_profile is None:
|
||||
raise RuntimeError(f"{self}: rs_profile must be initialized before use.")
|
||||
@@ -378,14 +377,12 @@ class RealSenseCamera(Camera):
|
||||
device = self.rs_profile.get_device()
|
||||
sensors = {s.get_info(rs.camera_info.name): s for s in device.query_sensors()}
|
||||
|
||||
if "RGB Camera" in sensors:
|
||||
return sensors["RGB Camera"]
|
||||
for name in ("RGB Camera", "Stereo Module"):
|
||||
if name in sensors:
|
||||
return sensors[name]
|
||||
|
||||
available = list(sensors.keys())
|
||||
raise RuntimeError(
|
||||
f"{self}: manual color controls require a dedicated 'RGB Camera' module, which this camera does not have. ",
|
||||
f"Available sensors: {available}.",
|
||||
)
|
||||
raise RuntimeError(f"{self}: no color sensor found. 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(
|
||||
|
||||
@@ -163,10 +163,8 @@ class PreTrainedConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC): # type: igno
|
||||
return None
|
||||
|
||||
def _save_pretrained(self, save_directory: Path) -> None:
|
||||
# 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)
|
||||
with open(save_directory / CONFIG_NAME, "w") as f, draccus.config_type("json"):
|
||||
draccus.dump(self, f, indent=4)
|
||||
|
||||
@classmethod
|
||||
def from_pretrained(
|
||||
|
||||
@@ -103,10 +103,8 @@ class RewardModelConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC):
|
||||
pass
|
||||
|
||||
def _save_pretrained(self, save_directory: Path) -> None:
|
||||
# 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)
|
||||
with open(save_directory / CONFIG_NAME, "w") as f, draccus.config_type("json"):
|
||||
draccus.dump(self, f, indent=4)
|
||||
|
||||
@classmethod
|
||||
def from_pretrained(
|
||||
|
||||
@@ -194,11 +194,7 @@ class TrainPipelineConfig(HubMixin):
|
||||
)
|
||||
|
||||
if Path(config_path).resolve().exists():
|
||||
# `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
|
||||
policy_dir = Path(config_path).parent
|
||||
self.checkpoint_path = policy_dir.parent
|
||||
elif self.job.is_remote:
|
||||
return
|
||||
|
||||
@@ -19,7 +19,6 @@ import copy
|
||||
import logging
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
from typing import Any, NotRequired, TypedDict
|
||||
|
||||
import datasets
|
||||
import pandas as pd
|
||||
@@ -50,32 +49,8 @@ from .utils import (
|
||||
)
|
||||
from .video_utils import concatenate_video_files, get_video_duration_in_s
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
type FeatureDict = dict[str, dict[str, Any]]
|
||||
type ChunkFile = tuple[int, int]
|
||||
|
||||
|
||||
class IndexState(TypedDict):
|
||||
chunk: int
|
||||
file: int
|
||||
src_to_dst: NotRequired[dict[ChunkFile, ChunkFile]]
|
||||
|
||||
|
||||
class VideoIndex(TypedDict):
|
||||
chunk: int
|
||||
file: int
|
||||
latest_duration: float
|
||||
episode_duration: float
|
||||
src_to_offset: NotRequired[dict[ChunkFile, float]]
|
||||
src_to_dst: NotRequired[dict[ChunkFile, ChunkFile]]
|
||||
dst_file_durations: NotRequired[dict[ChunkFile, float]]
|
||||
|
||||
|
||||
type VideoIndexState = dict[str, VideoIndex]
|
||||
|
||||
|
||||
def merge_video_feature_info_for_aggregate(all_metadata: list[LeRobotDatasetMetadata]) -> FeatureDict:
|
||||
def merge_video_feature_info_for_aggregate(all_metadata: list[LeRobotDatasetMetadata]) -> dict[str, dict]:
|
||||
"""Create a merged video feature info dictionary for aggregation. The video encoder info is merged field-by-field: each key is kept only when every source agrees; otherwise that key is set to ``null`` (or ``{}`` for ``video.extra_options``) and a warning is logged.
|
||||
|
||||
Args:
|
||||
@@ -84,14 +59,14 @@ def merge_video_feature_info_for_aggregate(all_metadata: list[LeRobotDatasetMeta
|
||||
Returns:
|
||||
dict: A dictionary of merged video feature info.
|
||||
"""
|
||||
merged_info: FeatureDict = copy.deepcopy(all_metadata[0].features)
|
||||
merged_info = copy.deepcopy(all_metadata[0].features)
|
||||
video_keys = [k for k in merged_info if merged_info[k].get("dtype") == "video"]
|
||||
|
||||
for vk in video_keys:
|
||||
video_infos = [m.features.get(vk, {}).get("info") or {} for m in all_metadata]
|
||||
base_video_info = video_infos[0]
|
||||
|
||||
merged_encoder_info: dict[str, Any] = {}
|
||||
merged_encoder_info: dict = {}
|
||||
fallback_keys: list[str] = []
|
||||
for info_key in VIDEO_ENCODER_INFO_KEYS:
|
||||
values = [info.get(info_key, None) for info in video_infos]
|
||||
@@ -105,7 +80,7 @@ def merge_video_feature_info_for_aggregate(all_metadata: list[LeRobotDatasetMeta
|
||||
merged_encoder_info[info_key] = {} if info_key == "video.extra_options" else None
|
||||
|
||||
if fallback_keys:
|
||||
logger.warning(
|
||||
logging.warning(
|
||||
f"Merging heterogeneous or incomplete video encoder metadata for feature {vk}. "
|
||||
f"Setting these keys to null: {fallback_keys}.",
|
||||
)
|
||||
@@ -117,7 +92,7 @@ def merge_video_feature_info_for_aggregate(all_metadata: list[LeRobotDatasetMeta
|
||||
return merged_info
|
||||
|
||||
|
||||
def validate_all_metadata(all_metadata: list[LeRobotDatasetMetadata]) -> tuple[int, str | None, FeatureDict]:
|
||||
def validate_all_metadata(all_metadata: list[LeRobotDatasetMetadata]):
|
||||
"""Validates that all dataset metadata have consistent properties.
|
||||
|
||||
Ensures all datasets have the same fps, robot_type, and features to guarantee
|
||||
@@ -154,9 +129,7 @@ def validate_all_metadata(all_metadata: list[LeRobotDatasetMetadata]) -> tuple[i
|
||||
return fps, robot_type, features
|
||||
|
||||
|
||||
def update_data_df(
|
||||
df: pd.DataFrame, src_meta: LeRobotDatasetMetadata, dst_meta: LeRobotDatasetMetadata
|
||||
) -> pd.DataFrame:
|
||||
def update_data_df(df, src_meta, dst_meta):
|
||||
"""Updates a data DataFrame with new indices and task mappings for aggregation.
|
||||
|
||||
Adjusts episode indices, frame indices, and task indices to account for
|
||||
@@ -181,12 +154,12 @@ def update_data_df(
|
||||
|
||||
|
||||
def update_meta_data(
|
||||
df: pd.DataFrame,
|
||||
dst_meta: LeRobotDatasetMetadata,
|
||||
meta_idx: IndexState,
|
||||
data_idx: IndexState,
|
||||
videos_idx: VideoIndexState,
|
||||
) -> pd.DataFrame:
|
||||
df,
|
||||
dst_meta,
|
||||
meta_idx,
|
||||
data_idx,
|
||||
videos_idx,
|
||||
):
|
||||
"""Updates metadata DataFrame with new chunk, file, and timestamp indices.
|
||||
|
||||
Adjusts all indices and timestamps to account for previously aggregated
|
||||
@@ -316,7 +289,7 @@ def aggregate_datasets(
|
||||
chunk_size: int | None = None,
|
||||
concatenate_videos: bool = True,
|
||||
concatenate_data: bool = True,
|
||||
) -> None:
|
||||
):
|
||||
"""Aggregates multiple LeRobot datasets into a single unified dataset.
|
||||
|
||||
This is the main function that orchestrates the aggregation process by:
|
||||
@@ -336,7 +309,7 @@ def aggregate_datasets(
|
||||
concatenate_videos: When False, keep one mp4 per source file instead of packing into shards.
|
||||
concatenate_data: When False, keep one parquet per source file instead of packing into shards.
|
||||
"""
|
||||
logger.info("Start aggregate_datasets")
|
||||
logging.info("Start aggregate_datasets")
|
||||
|
||||
if data_files_size_in_mb is None:
|
||||
data_files_size_in_mb = DEFAULT_DATA_FILE_SIZE_IN_MB
|
||||
@@ -368,15 +341,15 @@ def aggregate_datasets(
|
||||
video_files_size_in_mb=video_files_size_in_mb,
|
||||
)
|
||||
|
||||
logger.info("Find all tasks")
|
||||
logging.info("Find all tasks")
|
||||
unique_tasks = pd.concat([m.tasks for m in all_metadata]).index.unique()
|
||||
dst_meta.tasks = pd.DataFrame(
|
||||
{"task_index": range(len(unique_tasks))}, index=pd.Index(unique_tasks, name="task")
|
||||
)
|
||||
|
||||
meta_idx: IndexState = {"chunk": 0, "file": 0}
|
||||
data_idx: IndexState = {"chunk": 0, "file": 0}
|
||||
videos_idx: VideoIndexState = {
|
||||
meta_idx = {"chunk": 0, "file": 0}
|
||||
data_idx = {"chunk": 0, "file": 0}
|
||||
videos_idx = {
|
||||
key: {"chunk": 0, "file": 0, "latest_duration": 0, "episode_duration": 0} for key in video_keys
|
||||
}
|
||||
|
||||
@@ -400,17 +373,12 @@ def aggregate_datasets(
|
||||
dst_meta.info.total_frames += src_meta.total_frames
|
||||
|
||||
finalize_aggregation(dst_meta, all_metadata)
|
||||
logger.info("Aggregation complete.")
|
||||
logging.info("Aggregation complete.")
|
||||
|
||||
|
||||
def aggregate_videos(
|
||||
src_meta: LeRobotDatasetMetadata,
|
||||
dst_meta: LeRobotDatasetMetadata,
|
||||
videos_idx: VideoIndexState,
|
||||
video_files_size_in_mb: float,
|
||||
chunk_size: int,
|
||||
concatenate_videos: bool = True,
|
||||
) -> VideoIndexState:
|
||||
src_meta, dst_meta, videos_idx, video_files_size_in_mb, chunk_size, concatenate_videos=True
|
||||
):
|
||||
"""Aggregates video chunks from a source dataset into the destination dataset.
|
||||
|
||||
Handles video file concatenation and rotation based on file size limits.
|
||||
@@ -438,16 +406,15 @@ def aggregate_videos(
|
||||
videos_idx[key]["dst_file_durations"] = {}
|
||||
|
||||
for key, video_idx in videos_idx.items():
|
||||
unique_chunk_file_pairs: list[ChunkFile] = sorted(
|
||||
{
|
||||
(chunk, file)
|
||||
for chunk, file in zip(
|
||||
src_meta.episodes[f"videos/{key}/chunk_index"],
|
||||
src_meta.episodes[f"videos/{key}/file_index"],
|
||||
strict=False,
|
||||
)
|
||||
}
|
||||
)
|
||||
unique_chunk_file_pairs = {
|
||||
(chunk, file)
|
||||
for chunk, file in zip(
|
||||
src_meta.episodes[f"videos/{key}/chunk_index"],
|
||||
src_meta.episodes[f"videos/{key}/file_index"],
|
||||
strict=False,
|
||||
)
|
||||
}
|
||||
unique_chunk_file_pairs = sorted(unique_chunk_file_pairs)
|
||||
|
||||
chunk_idx = video_idx["chunk"]
|
||||
file_idx = video_idx["file"]
|
||||
@@ -522,14 +489,7 @@ def aggregate_videos(
|
||||
return videos_idx
|
||||
|
||||
|
||||
def aggregate_data(
|
||||
src_meta: LeRobotDatasetMetadata,
|
||||
dst_meta: LeRobotDatasetMetadata,
|
||||
data_idx: IndexState,
|
||||
data_files_size_in_mb: float,
|
||||
chunk_size: int,
|
||||
concatenate_data: bool = True,
|
||||
) -> IndexState:
|
||||
def aggregate_data(src_meta, dst_meta, data_idx, data_files_size_in_mb, chunk_size, concatenate_data=True):
|
||||
"""Aggregates data chunks from a source dataset into the destination dataset.
|
||||
|
||||
Reads source data files, updates indices to match the aggregated dataset,
|
||||
@@ -550,16 +510,14 @@ def aggregate_data(
|
||||
Returns:
|
||||
dict: Updated data_idx with current chunk and file indices.
|
||||
"""
|
||||
unique_chunk_file_ids: list[ChunkFile] = sorted(
|
||||
{
|
||||
(c, f)
|
||||
for c, f in zip(
|
||||
src_meta.episodes["data/chunk_index"],
|
||||
src_meta.episodes["data/file_index"],
|
||||
strict=False,
|
||||
)
|
||||
}
|
||||
)
|
||||
unique_chunk_file_ids = {
|
||||
(c, f)
|
||||
for c, f in zip(
|
||||
src_meta.episodes["data/chunk_index"], src_meta.episodes["data/file_index"], strict=False
|
||||
)
|
||||
}
|
||||
|
||||
unique_chunk_file_ids = sorted(unique_chunk_file_ids)
|
||||
contains_images = len(dst_meta.image_keys) > 0
|
||||
|
||||
# retrieve features schema for proper image typing in parquet
|
||||
@@ -567,7 +525,7 @@ def aggregate_data(
|
||||
|
||||
# Track source to destination file mapping for metadata update
|
||||
# This is critical for handling datasets that are already results of a merge
|
||||
src_to_dst: dict[ChunkFile, ChunkFile] = {}
|
||||
src_to_dst: dict[tuple[int, int], tuple[int, int]] = {}
|
||||
|
||||
for src_chunk_idx, src_file_idx in unique_chunk_file_ids:
|
||||
src_path = src_meta.root / DEFAULT_DATA_PATH.format(
|
||||
@@ -606,13 +564,7 @@ def aggregate_data(
|
||||
return data_idx
|
||||
|
||||
|
||||
def aggregate_metadata(
|
||||
src_meta: LeRobotDatasetMetadata,
|
||||
dst_meta: LeRobotDatasetMetadata,
|
||||
meta_idx: IndexState,
|
||||
data_idx: IndexState,
|
||||
videos_idx: VideoIndexState,
|
||||
) -> IndexState:
|
||||
def aggregate_metadata(src_meta, dst_meta, meta_idx, data_idx, videos_idx):
|
||||
"""Aggregates metadata from a source dataset into the destination dataset.
|
||||
|
||||
Reads source metadata files, updates all indices and timestamps,
|
||||
@@ -628,16 +580,16 @@ def aggregate_metadata(
|
||||
Returns:
|
||||
dict: Updated meta_idx with current chunk and file indices.
|
||||
"""
|
||||
chunk_file_ids: list[ChunkFile] = sorted(
|
||||
{
|
||||
(c, f)
|
||||
for c, f in zip(
|
||||
src_meta.episodes["meta/episodes/chunk_index"],
|
||||
src_meta.episodes["meta/episodes/file_index"],
|
||||
strict=False,
|
||||
)
|
||||
}
|
||||
)
|
||||
chunk_file_ids = {
|
||||
(c, f)
|
||||
for c, f in zip(
|
||||
src_meta.episodes["meta/episodes/chunk_index"],
|
||||
src_meta.episodes["meta/episodes/file_index"],
|
||||
strict=False,
|
||||
)
|
||||
}
|
||||
|
||||
chunk_file_ids = sorted(chunk_file_ids)
|
||||
for chunk_idx, file_idx in chunk_file_ids:
|
||||
src_path = src_meta.root / DEFAULT_EPISODES_PATH.format(chunk_index=chunk_idx, file_index=file_idx)
|
||||
df = pd.read_parquet(src_path)
|
||||
@@ -670,16 +622,16 @@ def aggregate_metadata(
|
||||
def append_or_create_parquet_file(
|
||||
df: pd.DataFrame,
|
||||
src_path: Path,
|
||||
idx: IndexState,
|
||||
idx: dict[str, int],
|
||||
max_mb: float,
|
||||
chunk_size: int,
|
||||
default_path: str,
|
||||
contains_images: bool = False,
|
||||
aggr_root: Path | None = None,
|
||||
aggr_root: Path = None,
|
||||
hf_features: datasets.Features | None = None,
|
||||
concatenate: bool = True,
|
||||
one_row_group_per_episode: bool = False,
|
||||
) -> tuple[IndexState, ChunkFile]:
|
||||
) -> tuple[dict[str, int], tuple[int, int]]:
|
||||
"""Appends data to an existing parquet file or creates a new one based on size constraints.
|
||||
|
||||
Manages file rotation when size limits are exceeded to prevent individual files
|
||||
@@ -702,13 +654,7 @@ def append_or_create_parquet_file(
|
||||
Returns:
|
||||
tuple: (updated_idx, (dst_chunk, dst_file)) where updated_idx is the index dict
|
||||
and (dst_chunk, dst_file) is the actual destination file the data was written to.
|
||||
|
||||
Raises:
|
||||
ValueError: If aggr_root is not provided.
|
||||
"""
|
||||
if aggr_root is None:
|
||||
raise ValueError("aggr_root must be provided.")
|
||||
|
||||
dst_chunk, dst_file = idx["chunk"], idx["file"]
|
||||
dst_path = aggr_root / default_path.format(chunk_index=dst_chunk, file_index=dst_file)
|
||||
|
||||
@@ -752,9 +698,7 @@ def append_or_create_parquet_file(
|
||||
return idx, (dst_chunk, dst_file)
|
||||
|
||||
|
||||
def finalize_aggregation(
|
||||
aggr_meta: LeRobotDatasetMetadata, all_metadata: list[LeRobotDatasetMetadata]
|
||||
) -> None:
|
||||
def finalize_aggregation(aggr_meta, all_metadata):
|
||||
"""Finalizes the dataset aggregation by writing summary files and statistics.
|
||||
|
||||
Writes the tasks file, info file with total counts and splits, and
|
||||
@@ -764,16 +708,16 @@ def finalize_aggregation(
|
||||
aggr_meta: Aggregated dataset metadata.
|
||||
all_metadata: List of all source dataset metadata objects.
|
||||
"""
|
||||
logger.info("write tasks")
|
||||
logging.info("write tasks")
|
||||
write_tasks(aggr_meta.tasks, aggr_meta.root)
|
||||
|
||||
logger.info("write info")
|
||||
logging.info("write info")
|
||||
aggr_meta.info.total_tasks = len(aggr_meta.tasks)
|
||||
aggr_meta.info.total_episodes = sum(m.total_episodes for m in all_metadata)
|
||||
aggr_meta.info.total_frames = sum(m.total_frames for m in all_metadata)
|
||||
aggr_meta.info.splits = {"train": f"0:{sum(m.total_episodes for m in all_metadata)}"}
|
||||
write_info(aggr_meta.info, aggr_meta.root)
|
||||
|
||||
logger.info("write stats")
|
||||
logging.info("write stats")
|
||||
aggr_meta.stats = aggregate_stats([m.stats for m in all_metadata])
|
||||
write_stats(aggr_meta.stats, aggr_meta.root)
|
||||
|
||||
@@ -188,8 +188,8 @@ class LeRobotDatasetMetadata:
|
||||
def _load_metadata(self):
|
||||
self.info = load_info(self.root)
|
||||
check_version_compatibility(self.repo_id, self._version, CODEBASE_VERSION)
|
||||
self.tasks = load_tasks(self.root) if self.total_tasks > 0 else None
|
||||
self.episodes = load_episodes(self.root) if self.total_episodes > 0 else None
|
||||
self.tasks = load_tasks(self.root)
|
||||
self.episodes = load_episodes(self.root)
|
||||
self.stats = load_stats(self.root)
|
||||
|
||||
def ensure_readable(self) -> None:
|
||||
|
||||
@@ -1045,12 +1045,10 @@ def _copy_data_with_feature_changes(
|
||||
df[feature_name] = feature_values
|
||||
else:
|
||||
feature_slice = values[frame_idx:end_idx]
|
||||
if feature_slice.ndim == 1:
|
||||
df[feature_name] = feature_slice
|
||||
elif feature_slice.ndim == 2 and feature_slice.shape[1] == 1:
|
||||
if len(feature_slice.shape) > 1 and feature_slice.shape[1] == 1:
|
||||
df[feature_name] = feature_slice.flatten()
|
||||
else:
|
||||
df[feature_name] = list(feature_slice)
|
||||
df[feature_name] = feature_slice
|
||||
frame_idx = end_idx
|
||||
|
||||
# Write using the same chunk/file structure as source
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -58,10 +58,6 @@ 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
|
||||
@@ -182,7 +178,7 @@ 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:
|
||||
"""
|
||||
@@ -426,7 +422,10 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
else:
|
||||
frames_buffer.append(frame)
|
||||
break # random shard sampled, switch shard
|
||||
except _ShardExhaustedError:
|
||||
except (
|
||||
RuntimeError,
|
||||
StopIteration,
|
||||
): # NOTE: StopIteration inside a generator throws a RuntimeError since python 3.7
|
||||
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
|
||||
@@ -504,11 +503,7 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
|
||||
|
||||
def make_frame(self, dataset_iterator: Backtrackable) -> Generator:
|
||||
"""Makes a frame starting from a 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 = next(dataset_iterator)
|
||||
item = item_to_torch(item)
|
||||
|
||||
updates = [] # list of "updates" to apply to the item retrieved from hf_dataset (w/o camera features)
|
||||
|
||||
@@ -507,7 +507,7 @@ class MetaworldEnv(EnvConfig):
|
||||
class RoboCasaEnv(EnvConfig):
|
||||
task: str = "CloseFridge"
|
||||
fps: int = 20
|
||||
episode_length: int | None = None
|
||||
episode_length: int = 1000
|
||||
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.lerobot_types import RobotObservation
|
||||
from lerobot.types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv, parse_camera_names
|
||||
|
||||
@@ -384,12 +384,7 @@ class LiberoEnv(gym.Env):
|
||||
|
||||
def close(self):
|
||||
if self._env is not None:
|
||||
try:
|
||||
self._env.close()
|
||||
finally:
|
||||
# LIBERO deletes its inner env on close, so this wrapper must
|
||||
# be recreated before the next reset.
|
||||
self._env = None
|
||||
self._env.close()
|
||||
|
||||
|
||||
def _make_env_fns(
|
||||
|
||||
@@ -25,7 +25,7 @@ import metaworld.policies as policies
|
||||
import numpy as np
|
||||
from gymnasium import spaces
|
||||
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
from 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.lerobot_types import RobotObservation
|
||||
from lerobot.types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv, parse_camera_names
|
||||
|
||||
@@ -98,19 +98,6 @@ 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.
|
||||
|
||||
@@ -167,7 +154,7 @@ 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 _get_task_horizon(task)
|
||||
self._max_episode_steps = episode_length if episode_length is not None else 1000
|
||||
|
||||
# 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.lerobot_types import RobotObservation
|
||||
from lerobot.types import RobotObservation
|
||||
from lerobot.utils.import_utils import _scipy_available
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv
|
||||
@@ -384,9 +384,7 @@ class RoboTwinEnv(gym.Env):
|
||||
|
||||
self._env: Any | None = None # deferred — created on first reset() inside worker
|
||||
self._step_count: int = 0
|
||||
self._black_frame: np.ndarray = np.zeros(
|
||||
(self.observation_height, self.observation_width, 3), dtype=np.uint8
|
||||
)
|
||||
self._black_frame = np.zeros((self.observation_height, self.observation_width, 3), dtype=np.uint8)
|
||||
|
||||
image_spaces = {
|
||||
cam: spaces.Box(
|
||||
|
||||
@@ -37,7 +37,7 @@ import numpy as np
|
||||
from gymnasium import spaces
|
||||
from scipy.spatial.transform import Rotation
|
||||
|
||||
from lerobot.lerobot_types import RobotObservation
|
||||
from lerobot.types import RobotObservation
|
||||
|
||||
from .utils import _LazyAsyncVectorEnv
|
||||
|
||||
@@ -373,7 +373,7 @@ class VLABenchEnv(gym.Env):
|
||||
|
||||
if action.shape[0] != 7:
|
||||
# Unknown layout — fall back to zero-pad so the sim doesn't crash.
|
||||
padded: np.ndarray = np.zeros(ctrl_dim, dtype=np.float64)
|
||||
padded = np.zeros(ctrl_dim, dtype=np.float64)
|
||||
padded[: min(action.shape[0], ctrl_dim)] = action[:ctrl_dim]
|
||||
return padded
|
||||
|
||||
|
||||
@@ -22,7 +22,6 @@ 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,
|
||||
@@ -32,6 +31,7 @@ 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
|
||||
|
||||
|
||||
@@ -42,9 +42,6 @@ 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()
|
||||
|
||||
@@ -21,7 +21,6 @@ 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,
|
||||
@@ -41,6 +40,7 @@ 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,
|
||||
@@ -302,33 +302,6 @@ def _pad_evo1_stats(
|
||||
return padded_stats
|
||||
|
||||
|
||||
def _refresh_evo1_normalization_steps(
|
||||
config: Evo1Config,
|
||||
preprocessor: PolicyProcessorPipeline,
|
||||
postprocessor: PolicyProcessorPipeline,
|
||||
) -> None:
|
||||
"""Re-pad checkpoint-loaded (un)normalizer stats/features to EVO1's fixed widths.
|
||||
|
||||
Loading a checkpoint injects the raw dataset stats (unpadded to max_state_dim/max_action_dim)
|
||||
into the (un)normalizer via the generic override path in make_pre_post_processors. Those stats
|
||||
and their declared features must be re-padded/reshaped to EVO1's fixed widths, otherwise
|
||||
normalization fails against the padded state/action tensors (e.g. state padded to 24 vs. 8-dim
|
||||
LIBERO stats). Padding is a no-op when stats are already at the target width.
|
||||
"""
|
||||
normalization_features = _evo1_normalization_features(config)
|
||||
action_features = _evo1_action_features(config)
|
||||
for step in preprocessor.steps:
|
||||
if isinstance(step, NormalizerProcessorStep):
|
||||
step.features = normalization_features
|
||||
step.stats = _pad_evo1_stats(config, step.stats)
|
||||
step.to(device=step.device, dtype=step.dtype)
|
||||
for step in postprocessor.steps:
|
||||
if isinstance(step, UnnormalizerProcessorStep):
|
||||
step.features = action_features
|
||||
step.stats = _pad_evo1_stats(config, step.stats)
|
||||
step.to(device=step.device, dtype=step.dtype)
|
||||
|
||||
|
||||
def reconcile_evo1_processors(
|
||||
config: Evo1Config,
|
||||
preprocessor: PolicyProcessorPipeline,
|
||||
@@ -336,19 +309,16 @@ def reconcile_evo1_processors(
|
||||
) -> tuple[PolicyProcessorPipeline, PolicyProcessorPipeline]:
|
||||
"""Reconcile checkpoint-loaded pipelines with the current EVO1 config.
|
||||
|
||||
Three things cannot be restored from a serialized pipeline alone: the EVO1 batch converter
|
||||
(converters are plain functions and are never serialized), eval-time CLI overrides of the
|
||||
action postprocessing flags (`postprocess_action_dim`, `binarize_gripper`, `gripper_*`), and the
|
||||
(un)normalizer stats/features when the generic override path injects raw, unpadded dataset
|
||||
stats. This restores the converter, re-pads the normalization stats to EVO1's fixed widths, and
|
||||
rebuilds the action step from the current config so those overrides take effect.
|
||||
Two things cannot be restored from a serialized pipeline alone: the EVO1 batch converter
|
||||
(converters are plain functions and are never serialized), and eval-time CLI overrides of the
|
||||
action postprocessing flags (`postprocess_action_dim`, `binarize_gripper`, `gripper_*`). This
|
||||
restores the converter and rebuilds the action step from the current config so those overrides
|
||||
take effect.
|
||||
"""
|
||||
# Pipelines reloaded from a checkpoint come back with the default batch converter, which drops
|
||||
# non-observation extras (embodiment_id, state_mask, custom task fields) needed by EVO1.
|
||||
preprocessor.to_transition = evo1_batch_to_transition
|
||||
|
||||
_refresh_evo1_normalization_steps(config, preprocessor, postprocessor)
|
||||
|
||||
action_step = Evo1ActionProcessorStep(
|
||||
action_dim=_evo1_action_dim(config),
|
||||
binarize_gripper=config.binarize_gripper,
|
||||
|
||||
@@ -28,7 +28,6 @@ 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,
|
||||
@@ -38,6 +37,7 @@ 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,
|
||||
|
||||
@@ -68,9 +68,6 @@ 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")
|
||||
|
||||
@@ -50,7 +50,6 @@ if TYPE_CHECKING or _datasets_available:
|
||||
else:
|
||||
LeRobotDataset = None
|
||||
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AbsoluteActionsProcessorStep,
|
||||
AddBatchDimensionProcessorStep,
|
||||
@@ -67,6 +66,7 @@ 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,
|
||||
|
||||
@@ -520,9 +520,6 @@ 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,
|
||||
|
||||
@@ -36,7 +36,6 @@ 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,
|
||||
@@ -50,6 +49,7 @@ 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,
|
||||
|
||||
@@ -749,9 +749,6 @@ class PI0Policy(PreTrainedPolicy):
|
||||
config_class = PI0Config
|
||||
name = "pi0"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: PI0Config,
|
||||
|
||||
@@ -714,9 +714,6 @@ class PI05Policy(PreTrainedPolicy):
|
||||
config_class = PI05Config
|
||||
name = "pi05"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: PI05Config,
|
||||
|
||||
@@ -22,7 +22,6 @@ 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,
|
||||
@@ -34,6 +33,7 @@ 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
|
||||
|
||||
@@ -22,7 +22,6 @@ 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,
|
||||
@@ -35,6 +34,7 @@ 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
|
||||
|
||||
@@ -249,10 +249,6 @@ 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]:
|
||||
|
||||
@@ -145,9 +145,6 @@ class SmolVLAPolicy(PreTrainedPolicy):
|
||||
config_class = SmolVLAConfig
|
||||
name = "smolvla"
|
||||
|
||||
def supports_rtc(self) -> bool:
|
||||
return True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: SmolVLAConfig,
|
||||
|
||||
@@ -168,23 +168,14 @@ class SmolVLMWithExpertModel(nn.Module):
|
||||
last_layers.append(self.num_vlm_layers - 2)
|
||||
frozen_layers = [
|
||||
"lm_head",
|
||||
"text_model.norm.weight",
|
||||
"text_model.model.norm.weight",
|
||||
]
|
||||
for layer in last_layers:
|
||||
frozen_layers.append(f"text_model.layers.{layer}.")
|
||||
frozen_layers.append(f"text_model.model.layers.{layer}.")
|
||||
|
||||
unmatched_patterns = set(frozen_layers)
|
||||
for name, params in self.vlm.named_parameters():
|
||||
matched_patterns = [k for k in frozen_layers if k in name]
|
||||
if matched_patterns:
|
||||
if any(k in name for k in frozen_layers):
|
||||
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.lerobot_types import PolicyAction, RobotAction, RobotObservation
|
||||
from lerobot.types import PolicyAction, RobotAction, RobotObservation
|
||||
from lerobot.utils.constants import ACTION, OBS_STR
|
||||
from lerobot.utils.feature_utils import build_dataset_frame
|
||||
|
||||
|
||||
@@ -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_prompt" not in name:
|
||||
if "soft_prompts" not in name:
|
||||
param.requires_grad = False
|
||||
|
||||
# Freeze or unfreeze soft prompts
|
||||
|
||||
@@ -21,7 +21,6 @@ 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,
|
||||
@@ -32,6 +31,7 @@ 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.lerobot_types import (
|
||||
from 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.lerobot_types import EnvTransition, PolicyAction
|
||||
from 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.lerobot_types import EnvTransition, PolicyAction, RobotAction, RobotObservation, TransitionKey
|
||||
from 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.lerobot_types import PolicyAction, RobotAction
|
||||
from 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.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
from 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.lerobot_types import PolicyAction, RobotAction, RobotObservation
|
||||
from 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.lerobot_types import EnvAction, EnvTransition, PolicyAction, TransitionKey
|
||||
from 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.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
from 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.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.types import EnvTransition, PolicyAction, TransitionKey
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
|
||||
@@ -45,14 +45,7 @@ from huggingface_hub import hf_hub_download
|
||||
from safetensors.torch import load_file, save_file
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import (
|
||||
EnvAction,
|
||||
EnvTransition,
|
||||
PolicyAction,
|
||||
RobotAction,
|
||||
RobotObservation,
|
||||
TransitionKey,
|
||||
)
|
||||
from lerobot.types import EnvAction, EnvTransition, PolicyAction, RobotAction, RobotObservation, TransitionKey
|
||||
from lerobot.utils.constants import HF_LEROBOT_HOME
|
||||
from lerobot.utils.hub import HubMixin
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ from typing import Any
|
||||
import torch
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import PolicyAction, RobotAction
|
||||
from 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.lerobot_types import EnvTransition, TransitionKey
|
||||
from 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.lerobot_types import EnvTransition, TransitionKey
|
||||
from 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.lerobot_types import EnvTransition, RobotObservation, TransitionKey
|
||||
from 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"
|
||||
|
||||
|
||||
@@ -25,7 +25,6 @@ from PIL import Image
|
||||
from torch import Tensor
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AddBatchDimensionProcessorStep,
|
||||
DeviceProcessorStep,
|
||||
@@ -40,6 +39,7 @@ from lerobot.rewards.robometer.configuration_robometer import (
|
||||
RobometerConfig,
|
||||
)
|
||||
from lerobot.rewards.robometer.modeling_robometer import ROBOMETER_FEATURE_PREFIX
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
OBS_IMAGES,
|
||||
POLICY_POSTPROCESSOR_DEFAULT_NAME,
|
||||
|
||||
@@ -47,7 +47,6 @@ else:
|
||||
Faker = None # type: ignore[assignment, misc]
|
||||
|
||||
from lerobot.configs import FeatureType, PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AddBatchDimensionProcessorStep,
|
||||
DeviceProcessorStep,
|
||||
@@ -59,6 +58,7 @@ from lerobot.processor import (
|
||||
policy_action_to_transition,
|
||||
transition_to_policy_action,
|
||||
)
|
||||
from lerobot.types import EnvTransition, PolicyAction, TransitionKey
|
||||
from lerobot.utils.constants import POLICY_POSTPROCESSOR_DEFAULT_NAME, POLICY_PREPROCESSOR_DEFAULT_NAME
|
||||
|
||||
from .configuration_sarm import SARMConfig
|
||||
|
||||
@@ -48,10 +48,10 @@ import torch
|
||||
from tqdm import tqdm
|
||||
|
||||
from lerobot.datasets import LeRobotDataset
|
||||
from lerobot.lerobot_types import TransitionKey
|
||||
from lerobot.rewards.topreward.configuration_topreward import TOPRewardConfig
|
||||
from lerobot.rewards.topreward.modeling_topreward import TOPRewardModel
|
||||
from lerobot.rewards.topreward.processor_topreward import TOPRewardEncoderProcessorStep
|
||||
from lerobot.types import TransitionKey
|
||||
|
||||
DEFAULT_OUTPUT_FILENAME = "topreward_progress.parquet"
|
||||
|
||||
|
||||
@@ -23,7 +23,6 @@ import torch
|
||||
from torch import Tensor
|
||||
|
||||
from lerobot.configs import PipelineFeatureType, PolicyFeature
|
||||
from lerobot.lerobot_types import EnvTransition, TransitionKey
|
||||
from lerobot.processor import (
|
||||
AddBatchDimensionProcessorStep,
|
||||
DeviceProcessorStep,
|
||||
@@ -38,6 +37,7 @@ from lerobot.rewards.topreward.configuration_topreward import (
|
||||
DEFAULT_PROMPT_SUFFIX_TEMPLATE,
|
||||
TOPRewardConfig,
|
||||
)
|
||||
from lerobot.types import EnvTransition, TransitionKey
|
||||
from lerobot.utils.constants import (
|
||||
OBS_IMAGES,
|
||||
OBS_PREFIX,
|
||||
|
||||
@@ -28,7 +28,7 @@ from huggingface_hub.errors import HfHubHTTPError
|
||||
from safetensors.torch import load_file as load_safetensors, save_file as save_safetensors
|
||||
from torch.optim import Optimizer
|
||||
|
||||
from lerobot.lerobot_types import BatchType
|
||||
from lerobot.types import BatchType
|
||||
from lerobot.utils.hub import HubMixin
|
||||
|
||||
from .configs import RLAlgorithmConfig, TrainingStats
|
||||
|
||||
@@ -16,7 +16,6 @@ from __future__ import annotations
|
||||
|
||||
import abc
|
||||
import builtins
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from dataclasses import dataclass, field
|
||||
@@ -79,10 +78,8 @@ class RLAlgorithmConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC):
|
||||
|
||||
def _save_pretrained(self, save_directory: Path) -> None:
|
||||
"""Serialize this config as ``config.json`` inside ``save_directory``."""
|
||||
# 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, RLAlgorithmConfig), f, indent=4)
|
||||
with open(save_directory / CONFIG_NAME, "w") as f, draccus.config_type("json"):
|
||||
draccus.dump(self, f, indent=4)
|
||||
|
||||
@classmethod
|
||||
def from_pretrained(
|
||||
|
||||
@@ -26,7 +26,6 @@ import torch.nn.functional as F # noqa: N812
|
||||
from torch import Tensor
|
||||
from torch.optim import Optimizer
|
||||
|
||||
from lerobot.lerobot_types import BatchType
|
||||
from lerobot.policies.gaussian_actor.modeling_gaussian_actor import (
|
||||
DISCRETE_DIMENSION_INDEX,
|
||||
MLP,
|
||||
@@ -36,6 +35,7 @@ from lerobot.policies.gaussian_actor.modeling_gaussian_actor import (
|
||||
orthogonal_init,
|
||||
)
|
||||
from lerobot.policies.utils import get_device_from_parameters
|
||||
from lerobot.types import BatchType
|
||||
from lerobot.utils.constants import ACTION
|
||||
from lerobot.utils.transition import move_state_dict_to_device
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ import functools
|
||||
import threading
|
||||
from collections.abc import Callable, Sequence
|
||||
from contextlib import suppress
|
||||
from typing import NotRequired, TypedDict
|
||||
from typing import TypedDict
|
||||
|
||||
import torch
|
||||
import torch.nn.functional as F # noqa: N812
|
||||
@@ -36,7 +36,7 @@ class BatchTransition(TypedDict):
|
||||
next_state: dict[str, torch.Tensor]
|
||||
done: torch.Tensor
|
||||
truncated: torch.Tensor
|
||||
complementary_info: NotRequired[dict[str, torch.Tensor | float | int] | None]
|
||||
complementary_info: dict[str, torch.Tensor | float | int] | None = None
|
||||
|
||||
|
||||
def random_crop_vectorized(images: torch.Tensor, output_size: tuple) -> torch.Tensor:
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from lerobot.lerobot_types import BatchType
|
||||
from lerobot.types import BatchType
|
||||
|
||||
from .data_mixer import DataMixer, OnlineOfflineMixer
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ from __future__ import annotations
|
||||
|
||||
import abc
|
||||
|
||||
from lerobot.lerobot_types import BatchType
|
||||
from lerobot.types import BatchType
|
||||
|
||||
from ..buffer import ReplayBuffer, concatenate_batch_transitions
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@ from __future__ import annotations
|
||||
from collections.abc import Iterator
|
||||
from typing import Any
|
||||
|
||||
from lerobot.lerobot_types import BatchType
|
||||
from lerobot.types import BatchType
|
||||
|
||||
from .algorithms.base import RLAlgorithm
|
||||
from .algorithms.configs import TrainingStats
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
import logging
|
||||
from functools import cached_property
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.bimanual import BimanualMixin
|
||||
from lerobot.utils.decorators import check_if_not_connected
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
import logging
|
||||
from functools import cached_property
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.bimanual import BimanualMixin
|
||||
from lerobot.utils.decorators import check_if_not_connected
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
import logging
|
||||
from functools import cached_property
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.bimanual import BimanualMixin
|
||||
from lerobot.utils.decorators import check_if_not_connected
|
||||
|
||||
@@ -62,7 +62,6 @@ class BiSOFollower(BimanualMixin, Robot):
|
||||
position_i_coefficient=config.left_arm_config.position_i_coefficient,
|
||||
position_d_coefficient=config.left_arm_config.position_d_coefficient,
|
||||
use_degrees=config.left_arm_config.use_degrees,
|
||||
num_read_retries=config.left_arm_config.num_read_retries,
|
||||
cameras=left_arm_cameras,
|
||||
)
|
||||
|
||||
@@ -76,7 +75,6 @@ class BiSOFollower(BimanualMixin, Robot):
|
||||
position_i_coefficient=config.right_arm_config.position_i_coefficient,
|
||||
position_d_coefficient=config.right_arm_config.position_d_coefficient,
|
||||
use_degrees=config.right_arm_config.use_degrees,
|
||||
num_read_retries=config.right_arm_config.num_read_retries,
|
||||
cameras=config.right_arm_config.cameras,
|
||||
)
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@ import cv2
|
||||
import numpy as np
|
||||
import requests
|
||||
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.decorators import check_if_already_connected, check_if_not_connected
|
||||
from lerobot.utils.errors import DeviceNotConnectedError
|
||||
|
||||
|
||||
@@ -19,12 +19,12 @@ import time
|
||||
from functools import cached_property
|
||||
|
||||
from lerobot.cameras import make_cameras_from_configs
|
||||
from lerobot.lerobot_types import RobotAction, RobotObservation
|
||||
from lerobot.motors import Motor, MotorNormMode
|
||||
from lerobot.motors.calibration_gui import RangeFinderGUI
|
||||
from lerobot.motors.feetech import (
|
||||
FeetechMotorsBus,
|
||||
)
|
||||
from lerobot.types import RobotAction, RobotObservation
|
||||
from lerobot.utils.decorators import check_if_already_connected, check_if_not_connected
|
||||
|
||||
from ..robot import Robot
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user