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 +70 -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 +64 -0
- checkpoint_005000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_005000/training_metadata.json +35 -0
- checkpoint_005000/training_state.pt +3 -0
- checkpoint_010000/config.json +70 -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 +64 -0
- checkpoint_010000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_010000/training_metadata.json +35 -0
- checkpoint_010000/training_state.pt +3 -0
- checkpoint_015000/config.json +70 -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 +64 -0
- checkpoint_015000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_015000/training_metadata.json +35 -0
- checkpoint_015000/training_state.pt +3 -0
- checkpoint_020000/config.json +70 -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 +64 -0
- checkpoint_020000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_020000/training_metadata.json +35 -0
- checkpoint_020000/training_state.pt +3 -0
- checkpoint_025000/config.json +70 -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 +64 -0
- checkpoint_025000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_025000/training_metadata.json +35 -0
- checkpoint_025000/training_state.pt +3 -0
- checkpoint_030000/config.json +70 -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 +64 -0
- checkpoint_030000/policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
- checkpoint_030000/training_metadata.json +35 -0
- checkpoint_030000/training_state.pt +3 -0
- checkpoint_035000/config.json +70 -0
- checkpoint_035000/model.safetensors +3 -0
checkpoint_005000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_005000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe467767d779e0796a2d62521a302d1dc4415bebf18a648666e72ff4f5559006
|
| 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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_005000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"action": {
|
| 49 |
+
"type": "ACTION",
|
| 50 |
+
"shape": [
|
| 51 |
+
6
|
| 52 |
+
]
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"norm_map": {
|
| 56 |
+
"VISUAL": "MEAN_STD",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 62 |
+
}
|
| 63 |
+
]
|
| 64 |
+
}
|
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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_005000/training_metadata.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_pos2_100ep",
|
| 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": 13700
|
| 35 |
+
}
|
checkpoint_005000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:451d288e35679d0f1a0e55dd286dd942f607219daa718c51a92fede08d8d49cc
|
| 3 |
+
size 412908960
|
checkpoint_010000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_010000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aab334cc727bc4559d3ff33ca681a6b3abec9176de986f2f98794814d4a8075
|
| 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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_010000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"action": {
|
| 49 |
+
"type": "ACTION",
|
| 50 |
+
"shape": [
|
| 51 |
+
6
|
| 52 |
+
]
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"norm_map": {
|
| 56 |
+
"VISUAL": "MEAN_STD",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 62 |
+
}
|
| 63 |
+
]
|
| 64 |
+
}
|
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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_010000/training_metadata.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_pos2_100ep",
|
| 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": 13700
|
| 35 |
+
}
|
checkpoint_010000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:044b49c8af62a7b508d4090e8e3b783f748658fbe217ad7bf2169d26dd4310f6
|
| 3 |
+
size 412908960
|
checkpoint_015000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_015000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e23e76bab6e785709da0faaa23a0d0e391b9f7af83763a90c559f390f373367f
|
| 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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_015000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"action": {
|
| 49 |
+
"type": "ACTION",
|
| 50 |
+
"shape": [
|
| 51 |
+
6
|
| 52 |
+
]
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"norm_map": {
|
| 56 |
+
"VISUAL": "MEAN_STD",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 62 |
+
}
|
| 63 |
+
]
|
| 64 |
+
}
|
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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_015000/training_metadata.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_pos2_100ep",
|
| 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": 13700
|
| 35 |
+
}
|
checkpoint_015000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94a002e605540c0b70f77dbc19ab021ff3ae85a4705a6fcf226c091d9392b2fb
|
| 3 |
+
size 412908960
|
checkpoint_020000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_020000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b262f8ff7830a1b095f47eba20298f53d9aa28d89a010f98c2131c49fefce31
|
| 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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_020000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"action": {
|
| 49 |
+
"type": "ACTION",
|
| 50 |
+
"shape": [
|
| 51 |
+
6
|
| 52 |
+
]
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"norm_map": {
|
| 56 |
+
"VISUAL": "MEAN_STD",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 62 |
+
}
|
| 63 |
+
]
|
| 64 |
+
}
|
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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_020000/training_metadata.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_pos2_100ep",
|
| 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": 13700
|
| 35 |
+
}
|
checkpoint_020000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a934486728f662762a64bc64a904c6c948e3c3c803f4d66630c8e3cfc80b6a9d
|
| 3 |
+
size 412908960
|
checkpoint_025000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_025000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0cf6dec147776dfcfdcfe651f46ec9bfa4f02c3fa4a704fd9e1d29af62556b3
|
| 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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_025000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"action": {
|
| 49 |
+
"type": "ACTION",
|
| 50 |
+
"shape": [
|
| 51 |
+
6
|
| 52 |
+
]
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"norm_map": {
|
| 56 |
+
"VISUAL": "MEAN_STD",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 62 |
+
}
|
| 63 |
+
]
|
| 64 |
+
}
|
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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_025000/training_metadata.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_pos2_100ep",
|
| 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": 13700
|
| 35 |
+
}
|
checkpoint_025000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e4ec5f3d9db6284a358f1a77f9d3cd12d80fb16fbcd5073d524a52457d86185
|
| 3 |
+
size 412908960
|
checkpoint_030000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_030000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68fe1068deae344e65538bb232ca6f3f11218954eba14dd02e145e446a8cfb0d
|
| 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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_030000/policy_preprocessor.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"action": {
|
| 49 |
+
"type": "ACTION",
|
| 50 |
+
"shape": [
|
| 51 |
+
6
|
| 52 |
+
]
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"norm_map": {
|
| 56 |
+
"VISUAL": "MEAN_STD",
|
| 57 |
+
"STATE": "MEAN_STD",
|
| 58 |
+
"ACTION": "MEAN_STD"
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
|
| 62 |
+
}
|
| 63 |
+
]
|
| 64 |
+
}
|
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:c71fb5729c86e7035beffea7a07fd91226bed9646b82ad9ed148759abf20f0c7
|
| 3 |
+
size 768
|
checkpoint_030000/training_metadata.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_pos2_100ep",
|
| 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": 13700
|
| 35 |
+
}
|
checkpoint_030000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:423456b20e2e9f834fd99e1b53ab74943fb07956960907ea12232d69de9bba78
|
| 3 |
+
size 412908960
|
checkpoint_035000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 28 |
+
"output_features": {
|
| 29 |
+
"action": {
|
| 30 |
+
"type": "ACTION",
|
| 31 |
+
"shape": [
|
| 32 |
+
6
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"device": "cuda",
|
| 37 |
+
"use_amp": false,
|
| 38 |
+
"push_to_hub": true,
|
| 39 |
+
"repo_id": null,
|
| 40 |
+
"private": null,
|
| 41 |
+
"tags": null,
|
| 42 |
+
"license": null,
|
| 43 |
+
"pretrained_path": null,
|
| 44 |
+
"chunk_size": 100,
|
| 45 |
+
"n_action_steps": 100,
|
| 46 |
+
"normalization_mapping": {
|
| 47 |
+
"VISUAL": "MEAN_STD",
|
| 48 |
+
"STATE": "MEAN_STD",
|
| 49 |
+
"ACTION": "MEAN_STD"
|
| 50 |
+
},
|
| 51 |
+
"vision_backbone": "resnet18",
|
| 52 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 53 |
+
"replace_final_stride_with_dilation": false,
|
| 54 |
+
"pre_norm": false,
|
| 55 |
+
"dim_model": 512,
|
| 56 |
+
"n_heads": 8,
|
| 57 |
+
"dim_feedforward": 3200,
|
| 58 |
+
"feedforward_activation": "relu",
|
| 59 |
+
"n_encoder_layers": 4,
|
| 60 |
+
"n_decoder_layers": 1,
|
| 61 |
+
"use_vae": true,
|
| 62 |
+
"latent_dim": 32,
|
| 63 |
+
"n_vae_encoder_layers": 4,
|
| 64 |
+
"temporal_ensemble_coeff": null,
|
| 65 |
+
"dropout": 0.1,
|
| 66 |
+
"kl_weight": 10.0,
|
| 67 |
+
"optimizer_lr": 1e-05,
|
| 68 |
+
"optimizer_weight_decay": 0.0001,
|
| 69 |
+
"optimizer_lr_backbone": 1e-05
|
| 70 |
+
}
|
checkpoint_035000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bdc432c4d22a11c5530a7975a6bb9948900403315e6a4c6b4530f785014ac00
|
| 3 |
+
size 206699736
|