Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint_005000/config.json +77 -0
- checkpoint_005000/model.safetensors +3 -0
- checkpoint_005000/policy_postprocessor.json +32 -0
- checkpoint_005000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoint_005000/policy_preprocessor.json +70 -0
- checkpoint_005000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_005000/training_metadata.json +36 -0
- checkpoint_005000/training_state.pt +3 -0
- checkpoint_010000/config.json +77 -0
- checkpoint_010000/model.safetensors +3 -0
- checkpoint_010000/policy_postprocessor.json +32 -0
- checkpoint_010000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoint_010000/policy_preprocessor.json +70 -0
- checkpoint_010000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_010000/training_metadata.json +36 -0
- checkpoint_010000/training_state.pt +3 -0
- checkpoint_015000/config.json +77 -0
- checkpoint_015000/model.safetensors +3 -0
- checkpoint_015000/policy_postprocessor.json +32 -0
- checkpoint_015000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoint_015000/policy_preprocessor.json +70 -0
- checkpoint_015000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_015000/training_metadata.json +36 -0
- checkpoint_015000/training_state.pt +3 -0
- checkpoint_020000/config.json +77 -0
- checkpoint_020000/model.safetensors +3 -0
- checkpoint_020000/policy_postprocessor.json +32 -0
- checkpoint_020000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoint_020000/policy_preprocessor.json +70 -0
- checkpoint_020000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_020000/training_metadata.json +36 -0
- checkpoint_020000/training_state.pt +3 -0
- checkpoint_025000/config.json +77 -0
- checkpoint_025000/model.safetensors +3 -0
- checkpoint_025000/policy_postprocessor.json +32 -0
- checkpoint_025000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoint_025000/policy_preprocessor.json +70 -0
- checkpoint_025000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_025000/training_metadata.json +36 -0
- checkpoint_025000/training_state.pt +3 -0
- checkpoint_030000/config.json +77 -0
- checkpoint_030000/model.safetensors +3 -0
- checkpoint_030000/policy_postprocessor.json +32 -0
- checkpoint_030000/policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
- checkpoint_030000/policy_preprocessor.json +70 -0
- checkpoint_030000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_030000/training_metadata.json +36 -0
- checkpoint_030000/training_state.pt +3 -0
- checkpoint_035000/config.json +77 -0
- checkpoint_035000/model.safetensors +3 -0
checkpoint_005000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_005000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2bffa1a38755fa42b0e6a448497b5a844ae1036b43fbd9d086d929aa9beae8a
|
| 3 |
+
size 206699736
|
checkpoint_005000/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "MEAN_STD",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoint_005000/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_005000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "device_processor",
|
| 16 |
+
"config": {
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"float_dtype": null
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"registry_name": "normalizer_processor",
|
| 23 |
+
"config": {
|
| 24 |
+
"eps": 1e-08,
|
| 25 |
+
"features": {
|
| 26 |
+
"observation.state": {
|
| 27 |
+
"type": "STATE",
|
| 28 |
+
"shape": [
|
| 29 |
+
6
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"observation.images.wrist_cam": {
|
| 33 |
+
"type": "VISUAL",
|
| 34 |
+
"shape": [
|
| 35 |
+
3,
|
| 36 |
+
480,
|
| 37 |
+
640
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
"observation.images.overhead_cam": {
|
| 41 |
+
"type": "VISUAL",
|
| 42 |
+
"shape": [
|
| 43 |
+
3,
|
| 44 |
+
480,
|
| 45 |
+
640
|
| 46 |
+
]
|
| 47 |
+
},
|
| 48 |
+
"observation.environment_state": {
|
| 49 |
+
"type": "STATE",
|
| 50 |
+
"shape": [
|
| 51 |
+
2
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
"action": {
|
| 55 |
+
"type": "ACTION",
|
| 56 |
+
"shape": [
|
| 57 |
+
6
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"norm_map": {
|
| 62 |
+
"VISUAL": "MEAN_STD",
|
| 63 |
+
"STATE": "MEAN_STD",
|
| 64 |
+
"ACTION": "MEAN_STD"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 68 |
+
}
|
| 69 |
+
]
|
| 70 |
+
}
|
checkpoint_005000/policy_preprocessor_step_3_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_005000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_220ep_confuser_mixed_5x",
|
| 3 |
+
"scene": "so101_with_wrist_cam.xml",
|
| 4 |
+
"scene_cameras": {
|
| 5 |
+
"overhead_cam": {
|
| 6 |
+
"fovy": 52.0,
|
| 7 |
+
"pos": [
|
| 8 |
+
0.3,
|
| 9 |
+
-0.09,
|
| 10 |
+
0.6
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"wrist_cam": {
|
| 14 |
+
"fovy": 71.0,
|
| 15 |
+
"pos": [
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0
|
| 19 |
+
]
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"cameras": [
|
| 23 |
+
"wrist_cam",
|
| 24 |
+
"overhead_cam"
|
| 25 |
+
],
|
| 26 |
+
"camera_resolutions": {
|
| 27 |
+
"wrist_cam": "640x480",
|
| 28 |
+
"overhead_cam": "640x480"
|
| 29 |
+
},
|
| 30 |
+
"action_space": "joint (6-dim: normalized joints)",
|
| 31 |
+
"action_dim": 6,
|
| 32 |
+
"chunk_size": 100,
|
| 33 |
+
"fps": 30,
|
| 34 |
+
"total_frames": 156050,
|
| 35 |
+
"pickup_coords": true
|
| 36 |
+
}
|
checkpoint_005000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e498e5ad31f45392accff1f3025d0986572cc96900e7fb047d205a89de66a468
|
| 3 |
+
size 412908960
|
checkpoint_010000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_010000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38d123f7a19dc26559106198adecc94aca2c2d4c7eb4bc2e803d1ba01213e2ad
|
| 3 |
+
size 206699736
|
checkpoint_010000/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "MEAN_STD",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoint_010000/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_010000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "device_processor",
|
| 16 |
+
"config": {
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"float_dtype": null
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"registry_name": "normalizer_processor",
|
| 23 |
+
"config": {
|
| 24 |
+
"eps": 1e-08,
|
| 25 |
+
"features": {
|
| 26 |
+
"observation.state": {
|
| 27 |
+
"type": "STATE",
|
| 28 |
+
"shape": [
|
| 29 |
+
6
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"observation.images.wrist_cam": {
|
| 33 |
+
"type": "VISUAL",
|
| 34 |
+
"shape": [
|
| 35 |
+
3,
|
| 36 |
+
480,
|
| 37 |
+
640
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
"observation.images.overhead_cam": {
|
| 41 |
+
"type": "VISUAL",
|
| 42 |
+
"shape": [
|
| 43 |
+
3,
|
| 44 |
+
480,
|
| 45 |
+
640
|
| 46 |
+
]
|
| 47 |
+
},
|
| 48 |
+
"observation.environment_state": {
|
| 49 |
+
"type": "STATE",
|
| 50 |
+
"shape": [
|
| 51 |
+
2
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
"action": {
|
| 55 |
+
"type": "ACTION",
|
| 56 |
+
"shape": [
|
| 57 |
+
6
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"norm_map": {
|
| 62 |
+
"VISUAL": "MEAN_STD",
|
| 63 |
+
"STATE": "MEAN_STD",
|
| 64 |
+
"ACTION": "MEAN_STD"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 68 |
+
}
|
| 69 |
+
]
|
| 70 |
+
}
|
checkpoint_010000/policy_preprocessor_step_3_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_010000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_220ep_confuser_mixed_5x",
|
| 3 |
+
"scene": "so101_with_wrist_cam.xml",
|
| 4 |
+
"scene_cameras": {
|
| 5 |
+
"overhead_cam": {
|
| 6 |
+
"fovy": 52.0,
|
| 7 |
+
"pos": [
|
| 8 |
+
0.3,
|
| 9 |
+
-0.09,
|
| 10 |
+
0.6
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"wrist_cam": {
|
| 14 |
+
"fovy": 71.0,
|
| 15 |
+
"pos": [
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0
|
| 19 |
+
]
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"cameras": [
|
| 23 |
+
"wrist_cam",
|
| 24 |
+
"overhead_cam"
|
| 25 |
+
],
|
| 26 |
+
"camera_resolutions": {
|
| 27 |
+
"wrist_cam": "640x480",
|
| 28 |
+
"overhead_cam": "640x480"
|
| 29 |
+
},
|
| 30 |
+
"action_space": "joint (6-dim: normalized joints)",
|
| 31 |
+
"action_dim": 6,
|
| 32 |
+
"chunk_size": 100,
|
| 33 |
+
"fps": 30,
|
| 34 |
+
"total_frames": 156050,
|
| 35 |
+
"pickup_coords": true
|
| 36 |
+
}
|
checkpoint_010000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a7db60ffcfe68c83f5333fba4ffc88257773c7da78df7c24aed766a5837a1d3
|
| 3 |
+
size 412908960
|
checkpoint_015000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_015000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2737e947b06b699a90c7205dbcdc31b03b25374d3db59d0459435f9d4a27434
|
| 3 |
+
size 206699736
|
checkpoint_015000/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "MEAN_STD",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoint_015000/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_015000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "device_processor",
|
| 16 |
+
"config": {
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"float_dtype": null
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"registry_name": "normalizer_processor",
|
| 23 |
+
"config": {
|
| 24 |
+
"eps": 1e-08,
|
| 25 |
+
"features": {
|
| 26 |
+
"observation.state": {
|
| 27 |
+
"type": "STATE",
|
| 28 |
+
"shape": [
|
| 29 |
+
6
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"observation.images.wrist_cam": {
|
| 33 |
+
"type": "VISUAL",
|
| 34 |
+
"shape": [
|
| 35 |
+
3,
|
| 36 |
+
480,
|
| 37 |
+
640
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
"observation.images.overhead_cam": {
|
| 41 |
+
"type": "VISUAL",
|
| 42 |
+
"shape": [
|
| 43 |
+
3,
|
| 44 |
+
480,
|
| 45 |
+
640
|
| 46 |
+
]
|
| 47 |
+
},
|
| 48 |
+
"observation.environment_state": {
|
| 49 |
+
"type": "STATE",
|
| 50 |
+
"shape": [
|
| 51 |
+
2
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
"action": {
|
| 55 |
+
"type": "ACTION",
|
| 56 |
+
"shape": [
|
| 57 |
+
6
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"norm_map": {
|
| 62 |
+
"VISUAL": "MEAN_STD",
|
| 63 |
+
"STATE": "MEAN_STD",
|
| 64 |
+
"ACTION": "MEAN_STD"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 68 |
+
}
|
| 69 |
+
]
|
| 70 |
+
}
|
checkpoint_015000/policy_preprocessor_step_3_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_015000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_220ep_confuser_mixed_5x",
|
| 3 |
+
"scene": "so101_with_wrist_cam.xml",
|
| 4 |
+
"scene_cameras": {
|
| 5 |
+
"overhead_cam": {
|
| 6 |
+
"fovy": 52.0,
|
| 7 |
+
"pos": [
|
| 8 |
+
0.3,
|
| 9 |
+
-0.09,
|
| 10 |
+
0.6
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"wrist_cam": {
|
| 14 |
+
"fovy": 71.0,
|
| 15 |
+
"pos": [
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0
|
| 19 |
+
]
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"cameras": [
|
| 23 |
+
"wrist_cam",
|
| 24 |
+
"overhead_cam"
|
| 25 |
+
],
|
| 26 |
+
"camera_resolutions": {
|
| 27 |
+
"wrist_cam": "640x480",
|
| 28 |
+
"overhead_cam": "640x480"
|
| 29 |
+
},
|
| 30 |
+
"action_space": "joint (6-dim: normalized joints)",
|
| 31 |
+
"action_dim": 6,
|
| 32 |
+
"chunk_size": 100,
|
| 33 |
+
"fps": 30,
|
| 34 |
+
"total_frames": 156050,
|
| 35 |
+
"pickup_coords": true
|
| 36 |
+
}
|
checkpoint_015000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cafeb12fd061e691e7201755c5f83cb40dad97bee5034694ce2b81ef61be3fb
|
| 3 |
+
size 412908960
|
checkpoint_020000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_020000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a46ba7f67ce9b78df4b8f9ede71745cbad61a35d405eac4fca01333306d422d
|
| 3 |
+
size 206699736
|
checkpoint_020000/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "MEAN_STD",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoint_020000/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_020000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "device_processor",
|
| 16 |
+
"config": {
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"float_dtype": null
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"registry_name": "normalizer_processor",
|
| 23 |
+
"config": {
|
| 24 |
+
"eps": 1e-08,
|
| 25 |
+
"features": {
|
| 26 |
+
"observation.state": {
|
| 27 |
+
"type": "STATE",
|
| 28 |
+
"shape": [
|
| 29 |
+
6
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"observation.images.wrist_cam": {
|
| 33 |
+
"type": "VISUAL",
|
| 34 |
+
"shape": [
|
| 35 |
+
3,
|
| 36 |
+
480,
|
| 37 |
+
640
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
"observation.images.overhead_cam": {
|
| 41 |
+
"type": "VISUAL",
|
| 42 |
+
"shape": [
|
| 43 |
+
3,
|
| 44 |
+
480,
|
| 45 |
+
640
|
| 46 |
+
]
|
| 47 |
+
},
|
| 48 |
+
"observation.environment_state": {
|
| 49 |
+
"type": "STATE",
|
| 50 |
+
"shape": [
|
| 51 |
+
2
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
"action": {
|
| 55 |
+
"type": "ACTION",
|
| 56 |
+
"shape": [
|
| 57 |
+
6
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"norm_map": {
|
| 62 |
+
"VISUAL": "MEAN_STD",
|
| 63 |
+
"STATE": "MEAN_STD",
|
| 64 |
+
"ACTION": "MEAN_STD"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 68 |
+
}
|
| 69 |
+
]
|
| 70 |
+
}
|
checkpoint_020000/policy_preprocessor_step_3_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_020000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_220ep_confuser_mixed_5x",
|
| 3 |
+
"scene": "so101_with_wrist_cam.xml",
|
| 4 |
+
"scene_cameras": {
|
| 5 |
+
"overhead_cam": {
|
| 6 |
+
"fovy": 52.0,
|
| 7 |
+
"pos": [
|
| 8 |
+
0.3,
|
| 9 |
+
-0.09,
|
| 10 |
+
0.6
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"wrist_cam": {
|
| 14 |
+
"fovy": 71.0,
|
| 15 |
+
"pos": [
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0
|
| 19 |
+
]
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"cameras": [
|
| 23 |
+
"wrist_cam",
|
| 24 |
+
"overhead_cam"
|
| 25 |
+
],
|
| 26 |
+
"camera_resolutions": {
|
| 27 |
+
"wrist_cam": "640x480",
|
| 28 |
+
"overhead_cam": "640x480"
|
| 29 |
+
},
|
| 30 |
+
"action_space": "joint (6-dim: normalized joints)",
|
| 31 |
+
"action_dim": 6,
|
| 32 |
+
"chunk_size": 100,
|
| 33 |
+
"fps": 30,
|
| 34 |
+
"total_frames": 156050,
|
| 35 |
+
"pickup_coords": true
|
| 36 |
+
}
|
checkpoint_020000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0388dc43d8caf1fd254d3342bc7ded2f6290a99ec48ad74d5d3dbfd0e5824ec3
|
| 3 |
+
size 412908960
|
checkpoint_025000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_025000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c62b1f01d702f483e9ea5b6789e4807f4d8303c34f7fc5a2a5fb39cba5df8a2
|
| 3 |
+
size 206699736
|
checkpoint_025000/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "MEAN_STD",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoint_025000/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_025000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "device_processor",
|
| 16 |
+
"config": {
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"float_dtype": null
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"registry_name": "normalizer_processor",
|
| 23 |
+
"config": {
|
| 24 |
+
"eps": 1e-08,
|
| 25 |
+
"features": {
|
| 26 |
+
"observation.state": {
|
| 27 |
+
"type": "STATE",
|
| 28 |
+
"shape": [
|
| 29 |
+
6
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"observation.images.wrist_cam": {
|
| 33 |
+
"type": "VISUAL",
|
| 34 |
+
"shape": [
|
| 35 |
+
3,
|
| 36 |
+
480,
|
| 37 |
+
640
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
"observation.images.overhead_cam": {
|
| 41 |
+
"type": "VISUAL",
|
| 42 |
+
"shape": [
|
| 43 |
+
3,
|
| 44 |
+
480,
|
| 45 |
+
640
|
| 46 |
+
]
|
| 47 |
+
},
|
| 48 |
+
"observation.environment_state": {
|
| 49 |
+
"type": "STATE",
|
| 50 |
+
"shape": [
|
| 51 |
+
2
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
"action": {
|
| 55 |
+
"type": "ACTION",
|
| 56 |
+
"shape": [
|
| 57 |
+
6
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"norm_map": {
|
| 62 |
+
"VISUAL": "MEAN_STD",
|
| 63 |
+
"STATE": "MEAN_STD",
|
| 64 |
+
"ACTION": "MEAN_STD"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 68 |
+
}
|
| 69 |
+
]
|
| 70 |
+
}
|
checkpoint_025000/policy_preprocessor_step_3_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_025000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_220ep_confuser_mixed_5x",
|
| 3 |
+
"scene": "so101_with_wrist_cam.xml",
|
| 4 |
+
"scene_cameras": {
|
| 5 |
+
"overhead_cam": {
|
| 6 |
+
"fovy": 52.0,
|
| 7 |
+
"pos": [
|
| 8 |
+
0.3,
|
| 9 |
+
-0.09,
|
| 10 |
+
0.6
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"wrist_cam": {
|
| 14 |
+
"fovy": 71.0,
|
| 15 |
+
"pos": [
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0
|
| 19 |
+
]
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"cameras": [
|
| 23 |
+
"wrist_cam",
|
| 24 |
+
"overhead_cam"
|
| 25 |
+
],
|
| 26 |
+
"camera_resolutions": {
|
| 27 |
+
"wrist_cam": "640x480",
|
| 28 |
+
"overhead_cam": "640x480"
|
| 29 |
+
},
|
| 30 |
+
"action_space": "joint (6-dim: normalized joints)",
|
| 31 |
+
"action_dim": 6,
|
| 32 |
+
"chunk_size": 100,
|
| 33 |
+
"fps": 30,
|
| 34 |
+
"total_frames": 156050,
|
| 35 |
+
"pickup_coords": true
|
| 36 |
+
}
|
checkpoint_025000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:608526e49d78a53bb57cbfdc96d3b6c5c38842da0356413b8c410535445470e5
|
| 3 |
+
size 412908960
|
checkpoint_030000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_030000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2167ccdb5fe0c599877360d8384e7ceb95780a5154e04a685f45ed32838ea092
|
| 3 |
+
size 206699736
|
checkpoint_030000/policy_postprocessor.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_postprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "unnormalizer_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"eps": 1e-08,
|
| 8 |
+
"features": {
|
| 9 |
+
"action": {
|
| 10 |
+
"type": "ACTION",
|
| 11 |
+
"shape": [
|
| 12 |
+
6
|
| 13 |
+
]
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"norm_map": {
|
| 17 |
+
"VISUAL": "MEAN_STD",
|
| 18 |
+
"STATE": "MEAN_STD",
|
| 19 |
+
"ACTION": "MEAN_STD"
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"registry_name": "device_processor",
|
| 26 |
+
"config": {
|
| 27 |
+
"device": "cpu",
|
| 28 |
+
"float_dtype": null
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
checkpoint_030000/policy_postprocessor_step_0_unnormalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_030000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "policy_preprocessor",
|
| 3 |
+
"steps": [
|
| 4 |
+
{
|
| 5 |
+
"registry_name": "rename_observations_processor",
|
| 6 |
+
"config": {
|
| 7 |
+
"rename_map": {}
|
| 8 |
+
}
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"registry_name": "to_batch_processor",
|
| 12 |
+
"config": {}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"registry_name": "device_processor",
|
| 16 |
+
"config": {
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"float_dtype": null
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"registry_name": "normalizer_processor",
|
| 23 |
+
"config": {
|
| 24 |
+
"eps": 1e-08,
|
| 25 |
+
"features": {
|
| 26 |
+
"observation.state": {
|
| 27 |
+
"type": "STATE",
|
| 28 |
+
"shape": [
|
| 29 |
+
6
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"observation.images.wrist_cam": {
|
| 33 |
+
"type": "VISUAL",
|
| 34 |
+
"shape": [
|
| 35 |
+
3,
|
| 36 |
+
480,
|
| 37 |
+
640
|
| 38 |
+
]
|
| 39 |
+
},
|
| 40 |
+
"observation.images.overhead_cam": {
|
| 41 |
+
"type": "VISUAL",
|
| 42 |
+
"shape": [
|
| 43 |
+
3,
|
| 44 |
+
480,
|
| 45 |
+
640
|
| 46 |
+
]
|
| 47 |
+
},
|
| 48 |
+
"observation.environment_state": {
|
| 49 |
+
"type": "STATE",
|
| 50 |
+
"shape": [
|
| 51 |
+
2
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
"action": {
|
| 55 |
+
"type": "ACTION",
|
| 56 |
+
"shape": [
|
| 57 |
+
6
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"norm_map": {
|
| 62 |
+
"VISUAL": "MEAN_STD",
|
| 63 |
+
"STATE": "MEAN_STD",
|
| 64 |
+
"ACTION": "MEAN_STD"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 68 |
+
}
|
| 69 |
+
]
|
| 70 |
+
}
|
checkpoint_030000/policy_preprocessor_step_3_normalizer_processor.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093ba7ded022004ae0677f281769ac9b3d2ebf5d656016400e4f7b66ec77f18a
|
| 3 |
+
size 7856
|
checkpoint_030000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_220ep_confuser_mixed_5x",
|
| 3 |
+
"scene": "so101_with_wrist_cam.xml",
|
| 4 |
+
"scene_cameras": {
|
| 5 |
+
"overhead_cam": {
|
| 6 |
+
"fovy": 52.0,
|
| 7 |
+
"pos": [
|
| 8 |
+
0.3,
|
| 9 |
+
-0.09,
|
| 10 |
+
0.6
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"wrist_cam": {
|
| 14 |
+
"fovy": 71.0,
|
| 15 |
+
"pos": [
|
| 16 |
+
0.0,
|
| 17 |
+
0.0,
|
| 18 |
+
0.0
|
| 19 |
+
]
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"cameras": [
|
| 23 |
+
"wrist_cam",
|
| 24 |
+
"overhead_cam"
|
| 25 |
+
],
|
| 26 |
+
"camera_resolutions": {
|
| 27 |
+
"wrist_cam": "640x480",
|
| 28 |
+
"overhead_cam": "640x480"
|
| 29 |
+
},
|
| 30 |
+
"action_space": "joint (6-dim: normalized joints)",
|
| 31 |
+
"action_dim": 6,
|
| 32 |
+
"chunk_size": 100,
|
| 33 |
+
"fps": 30,
|
| 34 |
+
"total_frames": 156050,
|
| 35 |
+
"pickup_coords": true
|
| 36 |
+
}
|
checkpoint_030000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85e9e73055992208275fb0be6d395e7dc9a1ea4275b3654e46944e83b59cdc85
|
| 3 |
+
size 412908960
|
checkpoint_035000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
6
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist_cam": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
480,
|
| 16 |
+
640
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.overhead_cam": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
480,
|
| 24 |
+
640
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.environment_state": {
|
| 28 |
+
"type": "STATE",
|
| 29 |
+
"shape": [
|
| 30 |
+
2
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"output_features": {
|
| 35 |
+
"action": {
|
| 36 |
+
"type": "ACTION",
|
| 37 |
+
"shape": [
|
| 38 |
+
6
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"device": "cuda",
|
| 43 |
+
"use_amp": false,
|
| 44 |
+
"use_peft": false,
|
| 45 |
+
"push_to_hub": true,
|
| 46 |
+
"repo_id": null,
|
| 47 |
+
"private": null,
|
| 48 |
+
"tags": null,
|
| 49 |
+
"license": null,
|
| 50 |
+
"pretrained_path": null,
|
| 51 |
+
"chunk_size": 100,
|
| 52 |
+
"n_action_steps": 100,
|
| 53 |
+
"normalization_mapping": {
|
| 54 |
+
"VISUAL": "MEAN_STD",
|
| 55 |
+
"STATE": "MEAN_STD",
|
| 56 |
+
"ACTION": "MEAN_STD"
|
| 57 |
+
},
|
| 58 |
+
"vision_backbone": "resnet18",
|
| 59 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 60 |
+
"replace_final_stride_with_dilation": false,
|
| 61 |
+
"pre_norm": false,
|
| 62 |
+
"dim_model": 512,
|
| 63 |
+
"n_heads": 8,
|
| 64 |
+
"dim_feedforward": 3200,
|
| 65 |
+
"feedforward_activation": "relu",
|
| 66 |
+
"n_encoder_layers": 4,
|
| 67 |
+
"n_decoder_layers": 1,
|
| 68 |
+
"use_vae": true,
|
| 69 |
+
"latent_dim": 32,
|
| 70 |
+
"n_vae_encoder_layers": 4,
|
| 71 |
+
"temporal_ensemble_coeff": null,
|
| 72 |
+
"dropout": 0.1,
|
| 73 |
+
"kl_weight": 10.0,
|
| 74 |
+
"optimizer_lr": 1e-05,
|
| 75 |
+
"optimizer_weight_decay": 0.0001,
|
| 76 |
+
"optimizer_lr_backbone": 1e-05
|
| 77 |
+
}
|
checkpoint_035000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a3a8874ba7e4d257e67eabd6333a4f57c074721ead88f2de56e4344b8943222
|
| 3 |
+
size 206699736
|