Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: jian001/record-GRC1
+library_name: lerobot
+license: apache-2.0
+model_name: diffusion
+pipeline_tag: robotics
+tags:
+- robotics
+- diffusion
+- lerobot
+---
+
+# Model Card for diffusion
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+[Diffusion Policy](https://huggingface.co/papers/2303.04137) treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation.
+
+
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+
+---
+
+## How to Get Started with the Model
+
+For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
+Below is the short version on how to train and run inference/eval:
+
+### Train from scratch
+
+```bash
+python -m lerobot.scripts.train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=act \
+  --output_dir=outputs/train/<desired_policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
+  --wandb.enable=true
+```
+
+*Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`.*
+
+### Evaluate the policy/run inference
+
+```bash
+python -m lerobot.record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
+```
+
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
+
+---
+
+## Model Details
+
+* **License:** apache-2.0

config.json

@@ -41,17 +41,17 @@
     "device": "cuda",
     "use_amp": false,
     "push_to_hub": true,
-    "repo_id": "/diffusion_so101_GRC1_model",
+    "repo_id": "jian001/diffusion_so101_GRC1",
     "private": null,
     "tags": null,
     "license": null,
-    "horizon": 16,
-    "n_action_steps": 8,
+    "horizon": 8,
+    "n_action_steps": 6,
     "drop_n_last_frames": 7,
     "vision_backbone": "resnet18",
     "crop_shape": [
-        84,
-        84
+        64,
+        64
     ],
     "crop_is_random": true,
     "pretrained_backbone_weights": null,
@@ -59,16 +59,16 @@
     "spatial_softmax_num_keypoints": 32,
     "use_separate_rgb_encoder_per_camera": false,
     "down_dims": [
+        256,
         512,
-        1024,
-        2048
+        1024
     ],
     "kernel_size": 5,
     "n_groups": 8,
     "diffusion_step_embed_dim": 128,
     "use_film_scale_modulation": true,
     "noise_scheduler_type": "DDPM",
-    "num_train_timesteps": 100,
+    "num_train_timesteps": 40,
     "beta_schedule": "squaredcos_cap_v2",
     "beta_start": 0.0001,
     "beta_end": 0.02,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08e1b92d168a6edfad4019ee5de0a9fc9f02402d458d0edfd7c41222f8844d5
-size 1066517736
+oid sha256:b9958dca125c1e7046fc7053ed7f10c686e90d439766aed8a30eacd7d09c70e4
+size 312135688

train_config.json

@@ -1,6 +1,6 @@
 {
     "dataset": {
-        "repo_id": "/record-GRC1",
+        "repo_id": "jian001/record-GRC1",
         "root": "/home/shitao/.cache/huggingface/lerobot/jian001/record-GRC1",
         "episodes": null,
         "image_transforms": {
@@ -108,17 +108,17 @@
         "device": "cuda",
         "use_amp": false,
         "push_to_hub": true,
-        "repo_id": "/diffusion_so101_GRC1_model",
+        "repo_id": "jian001/diffusion_so101_GRC1",
         "private": null,
         "tags": null,
         "license": null,
-        "horizon": 16,
-        "n_action_steps": 8,
+        "horizon": 8,
+        "n_action_steps": 6,
         "drop_n_last_frames": 7,
         "vision_backbone": "resnet18",
         "crop_shape": [
-            84,
-            84
+            64,
+            64
         ],
         "crop_is_random": true,
         "pretrained_backbone_weights": null,
@@ -126,16 +126,16 @@
         "spatial_softmax_num_keypoints": 32,
         "use_separate_rgb_encoder_per_camera": false,
         "down_dims": [
+            256,
             512,
-            1024,
-            2048
+            1024
         ],
         "kernel_size": 5,
         "n_groups": 8,
         "diffusion_step_embed_dim": 128,
         "use_film_scale_modulation": true,
         "noise_scheduler_type": "DDPM",
-        "num_train_timesteps": 100,
+        "num_train_timesteps": 40,
         "beta_schedule": "squaredcos_cap_v2",
         "beta_start": 0.0001,
         "beta_end": 0.02,
@@ -159,8 +159,8 @@
     "resume": false,
     "seed": 1000,
     "num_workers": 4,
-    "batch_size": 8,
-    "steps": 100000,
+    "batch_size": 12,
+    "steps": 30000,
     "eval_freq": 20000,
     "log_freq": 200,
     "save_checkpoint": true,
@@ -193,7 +193,7 @@
         "project": "lerobot",
         "entity": null,
         "notes": null,
-        "run_id": "tiea7xim",
+        "run_id": "nmle884x",
         "mode": null
     }
 }