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 sha256:70bf999ba1c1eec7050b8e6eac0af03f4c0034216aa057cf42a43064d7f27637
|
| 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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
checkpoint_005000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 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": 22534,
|
| 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:af7a46bae81550e5568d3f2ca9caab98c74199482d2dc012a62b7ff0f7694ca8
|
| 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:f2483a0ee39c1c5d41a2d3bf529c66a9db089fa625384741353c17735c05d0bd
|
| 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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
checkpoint_010000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 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": 22534,
|
| 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 sha256:149f80fcf0394682a2999d714bae676faa47d4ff45fc0efd7cee38be7783c934
|
| 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 sha256:721e9618d89012b43ce39992304f149d5e019052f265cfed2ead1baa3d2155ac
|
| 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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
checkpoint_015000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 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": 22534,
|
| 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:ef47992d02e97bad61a73c0f8e309bb5992854113637b33259587a22b4f5ca1d
|
| 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:d6dd1d0caf7c56b41f04239dd3ee055c6f9a7ac0bcc01e8a22b6dbddac310ca7
|
| 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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
checkpoint_020000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 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": 22534,
|
| 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 sha256:906bdc6e819b00798957efa05bb0322ab74adaf27d3d1fd122cd5c2d9338ed23
|
| 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 sha256:1207fd65a4d88442158a6a7636f4eac06d564ce50f5e9acec036950807439a13
|
| 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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
checkpoint_025000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 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": 22534,
|
| 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 sha256:4512077f830a32c7b6afbc78ff58c0d4f9490ccfc30e6f5ab16252931b8447b6
|
| 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 sha256:75f47391b271b566480229618af56e2cb5fc1d0dc40edbf2b7ca8205e0f1ad9d
|
| 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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
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 sha256:731ccfe10cfcaec1785fa0d13ef572a513213a2b13bd23abd9bac9015a1bc887
|
| 3 |
+
size 1384
|
checkpoint_030000/training_metadata.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 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": 22534,
|
| 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:e4396e6ea8e58de6ac3e60ba2f750d79805065a05876d94f7d13cde1135754a4
|
| 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 sha256:59fe0cfd16427f10710b3474442250818c951bdcdffa652dafa7a6a0b0fe5c29
|
| 3 |
+
size 206699736
|