Instructions to use open-cloth/diffusion-cloth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use open-cloth/diffusion-cloth with LeRobot:
- Notebooks
- Google Colab
- Kaggle
Upload policy weights, train config and readme
Browse files- config.json +5 -5
- model.safetensors +2 -2
- train_config.json +7 -7
config.json
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
"device": "cuda",
|
| 29 |
-
"use_amp":
|
| 30 |
"use_peft": false,
|
| 31 |
"push_to_hub": true,
|
| 32 |
"repo_id": "open-cloth/diffusion-cloth",
|
|
@@ -42,7 +42,7 @@
|
|
| 42 |
"ACTION": "MIN_MAX"
|
| 43 |
},
|
| 44 |
"drop_n_last_frames": 7,
|
| 45 |
-
"vision_backbone": "
|
| 46 |
"resize_shape": [
|
| 47 |
240,
|
| 48 |
320
|
|
@@ -53,14 +53,14 @@
|
|
| 53 |
288
|
| 54 |
],
|
| 55 |
"crop_is_random": true,
|
| 56 |
-
"pretrained_backbone_weights": "
|
| 57 |
"use_group_norm": false,
|
| 58 |
"spatial_softmax_num_keypoints": 64,
|
| 59 |
"use_separate_rgb_encoder_per_camera": false,
|
| 60 |
"down_dims": [
|
|
|
|
| 61 |
512,
|
| 62 |
-
1024
|
| 63 |
-
2048
|
| 64 |
],
|
| 65 |
"kernel_size": 5,
|
| 66 |
"n_groups": 8,
|
|
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
"device": "cuda",
|
| 29 |
+
"use_amp": true,
|
| 30 |
"use_peft": false,
|
| 31 |
"push_to_hub": true,
|
| 32 |
"repo_id": "open-cloth/diffusion-cloth",
|
|
|
|
| 42 |
"ACTION": "MIN_MAX"
|
| 43 |
},
|
| 44 |
"drop_n_last_frames": 7,
|
| 45 |
+
"vision_backbone": "resnet18",
|
| 46 |
"resize_shape": [
|
| 47 |
240,
|
| 48 |
320
|
|
|
|
| 53 |
288
|
| 54 |
],
|
| 55 |
"crop_is_random": true,
|
| 56 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 57 |
"use_group_norm": false,
|
| 58 |
"spatial_softmax_num_keypoints": 64,
|
| 59 |
"use_separate_rgb_encoder_per_camera": false,
|
| 60 |
"down_dims": [
|
| 61 |
+
256,
|
| 62 |
512,
|
| 63 |
+
1024
|
|
|
|
| 64 |
],
|
| 65 |
"kernel_size": 5,
|
| 66 |
"n_groups": 8,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5721932efb6c34a538d253578375c75fd0f2d79390fd8564dfa061940df0a96e
|
| 3 |
+
size 312295392
|
train_config.json
CHANGED
|
@@ -108,7 +108,7 @@
|
|
| 108 |
}
|
| 109 |
},
|
| 110 |
"device": "cuda",
|
| 111 |
-
"use_amp":
|
| 112 |
"use_peft": false,
|
| 113 |
"push_to_hub": true,
|
| 114 |
"repo_id": "open-cloth/diffusion-cloth",
|
|
@@ -124,7 +124,7 @@
|
|
| 124 |
"ACTION": "MIN_MAX"
|
| 125 |
},
|
| 126 |
"drop_n_last_frames": 7,
|
| 127 |
-
"vision_backbone": "
|
| 128 |
"resize_shape": [
|
| 129 |
240,
|
| 130 |
320
|
|
@@ -135,14 +135,14 @@
|
|
| 135 |
288
|
| 136 |
],
|
| 137 |
"crop_is_random": true,
|
| 138 |
-
"pretrained_backbone_weights": "
|
| 139 |
"use_group_norm": false,
|
| 140 |
"spatial_softmax_num_keypoints": 64,
|
| 141 |
"use_separate_rgb_encoder_per_camera": false,
|
| 142 |
"down_dims": [
|
|
|
|
| 143 |
512,
|
| 144 |
-
1024
|
| 145 |
-
2048
|
| 146 |
],
|
| 147 |
"kernel_size": 5,
|
| 148 |
"n_groups": 8,
|
|
@@ -175,7 +175,7 @@
|
|
| 175 |
"resume": false,
|
| 176 |
"seed": 1000,
|
| 177 |
"cudnn_deterministic": false,
|
| 178 |
-
"num_workers":
|
| 179 |
"batch_size": 64,
|
| 180 |
"steps": 200,
|
| 181 |
"eval_freq": 20000,
|
|
@@ -211,7 +211,7 @@
|
|
| 211 |
"project": "robot-learning",
|
| 212 |
"entity": null,
|
| 213 |
"notes": null,
|
| 214 |
-
"run_id": "
|
| 215 |
"mode": null,
|
| 216 |
"add_tags": true
|
| 217 |
},
|
|
|
|
| 108 |
}
|
| 109 |
},
|
| 110 |
"device": "cuda",
|
| 111 |
+
"use_amp": true,
|
| 112 |
"use_peft": false,
|
| 113 |
"push_to_hub": true,
|
| 114 |
"repo_id": "open-cloth/diffusion-cloth",
|
|
|
|
| 124 |
"ACTION": "MIN_MAX"
|
| 125 |
},
|
| 126 |
"drop_n_last_frames": 7,
|
| 127 |
+
"vision_backbone": "resnet18",
|
| 128 |
"resize_shape": [
|
| 129 |
240,
|
| 130 |
320
|
|
|
|
| 135 |
288
|
| 136 |
],
|
| 137 |
"crop_is_random": true,
|
| 138 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 139 |
"use_group_norm": false,
|
| 140 |
"spatial_softmax_num_keypoints": 64,
|
| 141 |
"use_separate_rgb_encoder_per_camera": false,
|
| 142 |
"down_dims": [
|
| 143 |
+
256,
|
| 144 |
512,
|
| 145 |
+
1024
|
|
|
|
| 146 |
],
|
| 147 |
"kernel_size": 5,
|
| 148 |
"n_groups": 8,
|
|
|
|
| 175 |
"resume": false,
|
| 176 |
"seed": 1000,
|
| 177 |
"cudnn_deterministic": false,
|
| 178 |
+
"num_workers": 22,
|
| 179 |
"batch_size": 64,
|
| 180 |
"steps": 200,
|
| 181 |
"eval_freq": 20000,
|
|
|
|
| 211 |
"project": "robot-learning",
|
| 212 |
"entity": null,
|
| 213 |
"notes": null,
|
| 214 |
+
"run_id": "njbxluis",
|
| 215 |
"mode": null,
|
| 216 |
"add_tags": true
|
| 217 |
},
|