Migrate policy to processor pipeline system This commit includes: - Preprocessor configuration - Postprocessor configuration - Clean model weights - Updated configurations - Model card

README.md

@@ -1,13 +1,13 @@
 ---
-datasets: AdilZtn/grab_red_cube_test_25
+datasets: unknown
 library_name: lerobot
 license: apache-2.0
 model_name: act
 pipeline_tag: robotics
 tags:
 - act
-- lerobot
 - robotics
+- lerobot
 ---
 
 # Model Card for act
@@ -31,7 +31,7 @@ Below is the short version on how to train and run inference/eval:
 ### Train from scratch
 
 ```bash
-python -m lerobot.scripts.train \
+lerobot-train \
   --dataset.repo_id=${HF_USER}/<dataset> \
   --policy.type=act \
   --output_dir=outputs/train/<desired_policy_repo_id> \
@@ -41,12 +41,12 @@ python -m lerobot.scripts.train \
   --wandb.enable=true
 ```
 
-*Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`.*
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
 
 ### Evaluate the policy/run inference
 
 ```bash
-python -m lerobot.record \
+lerobot-record \
   --robot.type=so100_follower \
   --dataset.repo_id=<hf_user>/eval_<dataset> \
   --policy.path=<hf_user>/<desired_policy_repo_id> \
@@ -59,4 +59,4 @@ Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a
 
 ## Model Details
 
-* **License:** apache-2.0
+- **License:** apache-2.0