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 +16 -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 +16 -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 +16 -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 +16 -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 +16 -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 +16 -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:d97d8bb12847afb378d282862aa1bb968f253ccdd04dd3e4f39f020132d7a05c
|
| 3 |
+
size 506085864
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
checkpoint_005000/training_metadata.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 3 |
+
"model_type": "act_vit",
|
| 4 |
+
"vision_backbone": "vit_b_16",
|
| 5 |
+
"cameras": [
|
| 6 |
+
"wrist_cam",
|
| 7 |
+
"overhead_cam"
|
| 8 |
+
],
|
| 9 |
+
"action_space": "joint (6-dim)",
|
| 10 |
+
"action_dim": 6,
|
| 11 |
+
"chunk_size": 100,
|
| 12 |
+
"fps": 30,
|
| 13 |
+
"total_frames": 22534,
|
| 14 |
+
"pickup_coords": false,
|
| 15 |
+
"pos1_only": false
|
| 16 |
+
}
|
checkpoint_005000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2283d06d9142d7332eac5fca69f184741a11c3ce39f133caa7e2824ad6c1ddcd
|
| 3 |
+
size 1011925005
|
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 sha256:380d52663faf262b8f4e2613cc4a32c7ead54b1d680c5097a9ca54912ca588e7
|
| 3 |
+
size 506085864
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
checkpoint_010000/training_metadata.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 3 |
+
"model_type": "act_vit",
|
| 4 |
+
"vision_backbone": "vit_b_16",
|
| 5 |
+
"cameras": [
|
| 6 |
+
"wrist_cam",
|
| 7 |
+
"overhead_cam"
|
| 8 |
+
],
|
| 9 |
+
"action_space": "joint (6-dim)",
|
| 10 |
+
"action_dim": 6,
|
| 11 |
+
"chunk_size": 100,
|
| 12 |
+
"fps": 30,
|
| 13 |
+
"total_frames": 22534,
|
| 14 |
+
"pickup_coords": false,
|
| 15 |
+
"pos1_only": false
|
| 16 |
+
}
|
checkpoint_010000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebb4598176db0baa90106b51458c8edc982372f0dc00bb49f8ea7629b12d2962
|
| 3 |
+
size 1011925005
|
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:ab4e743d65a0138abc331805d81ba6201bd700446b37bebb92eb4155c5acf430
|
| 3 |
+
size 506085864
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
checkpoint_015000/training_metadata.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 3 |
+
"model_type": "act_vit",
|
| 4 |
+
"vision_backbone": "vit_b_16",
|
| 5 |
+
"cameras": [
|
| 6 |
+
"wrist_cam",
|
| 7 |
+
"overhead_cam"
|
| 8 |
+
],
|
| 9 |
+
"action_space": "joint (6-dim)",
|
| 10 |
+
"action_dim": 6,
|
| 11 |
+
"chunk_size": 100,
|
| 12 |
+
"fps": 30,
|
| 13 |
+
"total_frames": 22534,
|
| 14 |
+
"pickup_coords": false,
|
| 15 |
+
"pos1_only": false
|
| 16 |
+
}
|
checkpoint_015000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeaf512cb5fa19f7d21d4baffeb935dfe078ff404282489bdf2b64433e8dd2bf
|
| 3 |
+
size 1011925005
|
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 sha256:05ac52a4fe6942c9460dd63526e228393e5b92df7ed1068db96b6c3f7660ed7b
|
| 3 |
+
size 506085864
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
checkpoint_020000/training_metadata.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 3 |
+
"model_type": "act_vit",
|
| 4 |
+
"vision_backbone": "vit_b_16",
|
| 5 |
+
"cameras": [
|
| 6 |
+
"wrist_cam",
|
| 7 |
+
"overhead_cam"
|
| 8 |
+
],
|
| 9 |
+
"action_space": "joint (6-dim)",
|
| 10 |
+
"action_dim": 6,
|
| 11 |
+
"chunk_size": 100,
|
| 12 |
+
"fps": 30,
|
| 13 |
+
"total_frames": 22534,
|
| 14 |
+
"pickup_coords": false,
|
| 15 |
+
"pos1_only": false
|
| 16 |
+
}
|
checkpoint_020000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:651bc50418ec042f5e3f33599b466899a4c05d101583d7f54d91a17e2830068a
|
| 3 |
+
size 1011925005
|
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 sha256:42d6a13a0ed3e1af646c207a21bacd92dc6944ca1554ea38a67398d8271d5cb6
|
| 3 |
+
size 506085864
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
checkpoint_025000/training_metadata.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 3 |
+
"model_type": "act_vit",
|
| 4 |
+
"vision_backbone": "vit_b_16",
|
| 5 |
+
"cameras": [
|
| 6 |
+
"wrist_cam",
|
| 7 |
+
"overhead_cam"
|
| 8 |
+
],
|
| 9 |
+
"action_space": "joint (6-dim)",
|
| 10 |
+
"action_dim": 6,
|
| 11 |
+
"chunk_size": 100,
|
| 12 |
+
"fps": 30,
|
| 13 |
+
"total_frames": 22534,
|
| 14 |
+
"pickup_coords": false,
|
| 15 |
+
"pos1_only": false
|
| 16 |
+
}
|
checkpoint_025000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cae0837efe37159ce13e37b31dec750c12b3c02888457eb8236193fe5afe4b6
|
| 3 |
+
size 1011925005
|
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:de8c8dae6df2c09c86fa032c04c852ba56d03f4dbe333603f4e8c5f35543b4cf
|
| 3 |
+
size 506085864
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
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:a6824ab6937ad18b00d079f86b6748e68addfe1a4ec2808ccc44376614bb0b45
|
| 3 |
+
size 1192
|
checkpoint_030000/training_metadata.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_repo_id": "danbhf/sim_pick_place_157ep",
|
| 3 |
+
"model_type": "act_vit",
|
| 4 |
+
"vision_backbone": "vit_b_16",
|
| 5 |
+
"cameras": [
|
| 6 |
+
"wrist_cam",
|
| 7 |
+
"overhead_cam"
|
| 8 |
+
],
|
| 9 |
+
"action_space": "joint (6-dim)",
|
| 10 |
+
"action_dim": 6,
|
| 11 |
+
"chunk_size": 100,
|
| 12 |
+
"fps": 30,
|
| 13 |
+
"total_frames": 22534,
|
| 14 |
+
"pickup_coords": false,
|
| 15 |
+
"pos1_only": false
|
| 16 |
+
}
|
checkpoint_030000/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee00e328d390be7441c502687f7c1f8339993ddad912ecc8a11a65f902fa044
|
| 3 |
+
size 1011925005
|
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 sha256:69669708471f57ea9ca735774f000c80b966121c826cc93c428598f43f9131a6
|
| 3 |
+
size 506085864
|