admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-29 04:36:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix old docs and comments

Browse Source
This commit is contained in:
Nikodem Bartnik
2026-07-28 14:31:30 +02:00
parent 258d521a89
commit 68d6335d5b
8 changed files with 26 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/act.mdx
+1 -1
View File
@@ -76,7 +76,7 @@ If your local computer doesn't have a powerful GPU, you can utilize Google Colab
## Evaluating ACT ## Evaluating ACT
Once training is complete, you can evaluate your ACT policy using the `lerobot-record` command with your trained policy. This will run inference and record evaluation episodes: Once training is complete, you can evaluate your ACT policy using the `lerobot-rollout` command with your trained policy. This will run inference and record evaluation episodes:
```bash ```bash
lerobot-rollout \ lerobot-rollout \
docs/source/earthrover_mini_plus.mdx
+1 -1
View File
@@ -194,8 +194,8 @@ lerobot-record \
--dataset.single_task="Navigate around obstacles" \ --dataset.single_task="Navigate around obstacles" \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
--dataset.encoder_threads=2 \ --dataset.encoder_threads=2 \
# --dataset.rgb_encoder.vcodec=auto \
--display_data=true --display_data=true
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
Replace `your_username/dataset_name` with your Hugging Face username and a name for your dataset. Replace `your_username/dataset_name` with your Hugging Face username and a name for your dataset.
docs/source/hope_jr.mdx
+2 -2
View File
@@ -232,8 +232,8 @@ lerobot-record \
--dataset.private=true \ --dataset.private=true \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
--dataset.encoder_threads=2 \ --dataset.encoder_threads=2 \
# --dataset.rgb_encoder.vcodec=auto \
--display_data=true --display_data=true
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
### Replay ### Replay
@@ -278,6 +278,6 @@ lerobot-record \
--dataset.num_episodes=10 \ --dataset.num_episodes=10 \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
--dataset.encoder_threads=2 \ --dataset.encoder_threads=2 \
# --dataset.rgb_encoder.vcodec=auto \
--policy.path=outputs/train/hopejr_hand/checkpoints/last/pretrained_model --policy.path=outputs/train/hopejr_hand/checkpoints/last/pretrained_model
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
docs/source/il_robots.mdx
+2 -2
View File
@@ -207,8 +207,8 @@ lerobot-record \
--dataset.num_episodes=5 \ --dataset.num_episodes=5 \
--dataset.single_task="Grab the black cube" \ --dataset.single_task="Grab the black cube" \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
# --dataset.rgb_encoder.vcodec=auto \
--dataset.encoder_threads=2 --dataset.encoder_threads=2
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
</hfoption> </hfoption>
<hfoption id="API example"> <hfoption id="API example">
@@ -418,7 +418,7 @@ If you want to dive deeper into this important topic, you can check out the [blo
## Visualize a dataset ## Visualize a dataset
If you uploaded your dataset to the hub with `--control.push_to_hub=true`, you can [visualize your dataset online](https://huggingface.co/spaces/lerobot/visualize_dataset) by copy pasting your repo id given by: If you uploaded your dataset to the hub with `--dataset.push_to_hub=true`, you can [visualize your dataset online](https://huggingface.co/spaces/lerobot/visualize_dataset) by copy pasting your repo id given by:
```bash ```bash
echo ${HF_USER}/so101_test echo ${HF_USER}/so101_test
docs/source/lerobot-dataset-v3.mdx
+1 -1
View File
@@ -44,8 +44,8 @@ lerobot-record \
--dataset.num_episodes=5 \ --dataset.num_episodes=5 \
--dataset.single_task="Grab the black cube" \ --dataset.single_task="Grab the black cube" \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
# --dataset.rgb_encoder.vcodec=auto \
--dataset.encoder_threads=2 --dataset.encoder_threads=2
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
See the [recording guide](./il_robots#record-a-dataset) for more details. See the [recording guide](./il_robots#record-a-dataset) for more details.
docs/source/openarm.mdx
+4 -3
View File
@@ -205,9 +205,10 @@ lerobot-record \
--teleop.type=openarm_leader \ --teleop.type=openarm_leader \
--teleop.port=can1 \ --teleop.port=can1 \
--teleop.id=my_leader \ --teleop.id=my_leader \
--repo-id=my_hf_username/my_openarm_dataset \ --dataset.repo_id=my_hf_username/my_openarm_dataset \
--fps=30 \ --dataset.single_task="Grab the black cube" \
--num-episodes=10 --dataset.fps=30 \
--dataset.num_episodes=10
``` ```
## Configuration Options ## Configuration Options
docs/source/reachy2.mdx
+2 -2
View File
@@ -161,8 +161,8 @@ lerobot-record \
--dataset.private=true \ --dataset.private=true \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
--dataset.encoder_threads=2 \ --dataset.encoder_threads=2 \
# --dataset.rgb_encoder.vcodec=auto \
--display_data=true --display_data=true
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
#### Specific Options #### Specific Options
@@ -203,8 +203,8 @@ lerobot-record \
--dataset.private=true \ --dataset.private=true \
--dataset.streaming_encoding=true \ --dataset.streaming_encoding=true \
--dataset.encoder_threads=2 \ --dataset.encoder_threads=2 \
# --dataset.rgb_encoder.vcodec=auto \
--display_data=true --display_data=true
# Optionally, set --dataset.rgb_encoder.vcodec=auto to pick a specific video codec
``` ```
##### `--robot.use_external_commands` ##### `--robot.use_external_commands`
docs/source/smolvla.mdx
+13 -14
View File
@@ -100,20 +100,19 @@ Once you are logged in, you can run inference in your setup by doing:
lerobot-rollout \ lerobot-rollout \
--strategy.type=base \ --strategy.type=base \
--robot.type=so101_follower \ --robot.type=so101_follower \
--robot.port=/dev/ttyACM0 \ # <- Use your port --robot.port=/dev/ttyACM0 \
--robot.id=my_blue_follower_arm \ # <- Use your robot id --robot.id=my_blue_follower_arm \
--robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras --robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \
--task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording --task="Grasp a lego block and put it in the bin." \
# <- RTC optional, use when running on low power hardware \ --policy.path=HF_USER/FINETUNE_MODEL_NAME
# --inference.type=rtc \
# --inference.rtc.execution_horizon=10 \
# --inference.rtc.max_guidance_weight=10.0 \
# <- Teleop optional if you want to teleoperate in between episodes \
# --teleop.type=so100_leader \
# --teleop.port=/dev/ttyACM0 \
# --teleop.id=my_red_leader_arm \
# --display_data=true #optional use if you want to see the camera stream \
--policy.path=HF_USER/FINETUNE_MODEL_NAME # <- Use your fine-tuned model
``` ```
Replace `--robot.port`, `--robot.id`, `--robot.cameras`, `--task`, and `--policy.path` with your own port, robot ID, camera setup, task description (matching what you used when recording your dataset), and fine-tuned model repo ID.
A few optional flags you can add to the command above:
- **RTC** (useful on low-power hardware): `--inference.type=rtc --inference.rtc.execution_horizon=10 --inference.rtc.max_guidance_weight=10.0`
- **Teleoperate in between episodes**: `--teleop.type=so100_leader --teleop.port=/dev/ttyACM0 --teleop.id=my_red_leader_arm`
- **See the camera stream**: `--display_data=true`
Depending on your evaluation setup, you can configure the duration and the number of episodes to record for your evaluation suite. Depending on your evaluation setup, you can configure the duration and the number of episodes to record for your evaluation suite.