Instructions to use wsagi/ACT-PickOrange with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use wsagi/ACT-PickOrange with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload config.json (v0.4.0 ckpt-18k)
Browse files- config.json +2 -3
config.json
CHANGED
|
@@ -35,13 +35,12 @@
|
|
| 35 |
},
|
| 36 |
"device": "cuda",
|
| 37 |
"use_amp": false,
|
| 38 |
-
"use_peft": false,
|
| 39 |
"push_to_hub": false,
|
| 40 |
"repo_id": null,
|
| 41 |
"private": null,
|
| 42 |
"tags": null,
|
| 43 |
"license": null,
|
| 44 |
-
"pretrained_path":
|
| 45 |
"chunk_size": 100,
|
| 46 |
"n_action_steps": 100,
|
| 47 |
"normalization_mapping": {
|
|
@@ -51,7 +50,7 @@
|
|
| 51 |
},
|
| 52 |
"vision_backbone": "resnet18",
|
| 53 |
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 54 |
-
"replace_final_stride_with_dilation":
|
| 55 |
"pre_norm": false,
|
| 56 |
"dim_model": 512,
|
| 57 |
"n_heads": 8,
|
|
|
|
| 35 |
},
|
| 36 |
"device": "cuda",
|
| 37 |
"use_amp": false,
|
|
|
|
| 38 |
"push_to_hub": false,
|
| 39 |
"repo_id": null,
|
| 40 |
"private": null,
|
| 41 |
"tags": null,
|
| 42 |
"license": null,
|
| 43 |
+
"pretrained_path": "LeIsaac/outputs/act-v040-baseline/checkpoints/last/pretrained_model",
|
| 44 |
"chunk_size": 100,
|
| 45 |
"n_action_steps": 100,
|
| 46 |
"normalization_mapping": {
|
|
|
|
| 50 |
},
|
| 51 |
"vision_backbone": "resnet18",
|
| 52 |
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": 0,
|
| 54 |
"pre_norm": false,
|
| 55 |
"dim_model": 512,
|
| 56 |
"n_heads": 8,
|