Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+library_name: lerobot
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+- robotics
+- dot
+license: apache-2.0
+datasets:
+- lerobot/aloha_sim_insertion_human
+pipeline_tag: robotics
+---
+
+# Model Card for "Decoder Only Transformer (DOT) Policy" for ALOHA bimanual insert problem
+
+Read more about the model and implementation details in the [DOT Policy repository](https://github.com/IliaLarchenko/dot_policy).
+
+This model is trained using the [LeRobot library](https://huggingface.co/lerobot) and achieves state-of-the-art results on behavior cloning on ALOHA bimanual insert dataset. It achieves 29.6% success rate vs. 21% for the previous state-of-the-art model (ACT).
+
+This result is achieved without the checkpoint selection and is easy to reproduce.
+
+You can use this model by installing LeRobot from [this branch](https://github.com/IliaLarchenko/lerobot/tree/dot)
+
+To train the model:
+
+```bash
+python lerobot/scripts/train.py policy=dot_insert env=aloha env.episode_length=500
+```
+
+To evaluate the model:
+
+```bash
+python lerobot/scripts/eval.py -p IliaLarchenko/dot_bimanual_insert eval.n_episodes=1000 eval.batch_size=100 seed=1000000
+```
+
+Model size:
+- Total parameters: 14.1m
+- Trainable parameters: 2.9m

config.json

@@ -0,0 +1,50 @@
+{
+  "alpha": 0.98,
+  "crop_scale": 0.8,
+  "dim_feedforward": 512,
+  "dim_model": 128,
+  "dropout": 0.1,
+  "inference_horizon": 100,
+  "input_normalization_modes": {
+    "observation.images.top": "mean_std",
+    "observation.state": "min_max"
+  },
+  "input_shapes": {
+    "observation.images.top": [
+      3,
+      480,
+      640
+    ],
+    "observation.state": [
+      14
+    ]
+  },
+  "lookback_aug": 5,
+  "lookback_obs_steps": 30,
+  "lora_rank": 20,
+  "merge_lora": true,
+  "n_decoder_layers": 8,
+  "n_heads": 8,
+  "n_obs_steps": 3,
+  "noise_decay": 0.999995,
+  "output_normalization_modes": {
+    "action": "min_max"
+  },
+  "output_shapes": {
+    "action": [
+      14
+    ]
+  },
+  "pre_norm": true,
+  "predict_every_n": 1,
+  "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+  "rescale_shape": [
+    480,
+    640
+  ],
+  "return_every_n": 1,
+  "state_noise": 0.01,
+  "train_alpha": 0.99,
+  "train_horizon": 150,
+  "vision_backbone": "resnet18"
+}

config.yaml

@@ -0,0 +1,322 @@
+resume: false
+device: cuda
+use_amp: true
+seed: 100000
+dataset_repo_id: lerobot/aloha_sim_insertion_human
+video_backend: pyav
+training:
+  offline_steps: 100000
+  num_workers: 12
+  batch_size: 12
+  eval_freq: 10000
+  log_freq: 1000
+  save_checkpoint: true
+  save_freq: 10000
+  online_steps: 0
+  online_rollout_n_episodes: 1
+  online_rollout_batch_size: 1
+  online_steps_between_rollouts: 1
+  online_sampling_ratio: 0.5
+  online_env_seed: null
+  online_buffer_capacity: null
+  online_buffer_seed_size: 0
+  do_online_rollout_async: false
+  image_transforms:
+    enable: false
+    max_num_transforms: 3
+    random_order: false
+    brightness:
+      weight: 1
+      min_max:
+      - 0.8
+      - 1.2
+    contrast:
+      weight: 1
+      min_max:
+      - 0.8
+      - 1.2
+    saturation:
+      weight: 1
+      min_max:
+      - 0.5
+      - 1.5
+    hue:
+      weight: 1
+      min_max:
+      - -0.05
+      - 0.05
+    sharpness:
+      weight: 1
+      min_max:
+      - 0.8
+      - 1.2
+  save_model: true
+  grad_clip_norm: 50
+  lr: 3.0e-05
+  min_lr: 1.0e-05
+  lr_cycle_steps: 100000
+  weight_decay: 1.0e-05
+  delta_timestamps:
+    observation.images.top:
+    - -0.7
+    - -0.68
+    - -0.66
+    - -0.64
+    - -0.62
+    - -0.6
+    - -0.58
+    - -0.56
+    - -0.54
+    - -0.52
+    - -0.5
+    - -0.02
+    - 0.0
+    observation.state:
+    - -0.7
+    - -0.68
+    - -0.66
+    - -0.64
+    - -0.62
+    - -0.6
+    - -0.58
+    - -0.56
+    - -0.54
+    - -0.52
+    - -0.5
+    - -0.02
+    - 0.0
+    action:
+    - -0.7
+    - -0.68
+    - -0.66
+    - -0.64
+    - -0.62
+    - -0.6
+    - -0.58
+    - -0.56
+    - -0.54
+    - -0.52
+    - -0.5
+    - -0.02
+    - 0.0
+    - 0.02
+    - 0.04
+    - 0.06
+    - 0.08
+    - 0.1
+    - 0.12
+    - 0.14
+    - 0.16
+    - 0.18
+    - 0.2
+    - 0.22
+    - 0.24
+    - 0.26
+    - 0.28
+    - 0.3
+    - 0.32
+    - 0.34
+    - 0.36
+    - 0.38
+    - 0.4
+    - 0.42
+    - 0.44
+    - 0.46
+    - 0.48
+    - 0.5
+    - 0.52
+    - 0.54
+    - 0.56
+    - 0.58
+    - 0.6
+    - 0.62
+    - 0.64
+    - 0.66
+    - 0.68
+    - 0.7
+    - 0.72
+    - 0.74
+    - 0.76
+    - 0.78
+    - 0.8
+    - 0.82
+    - 0.84
+    - 0.86
+    - 0.88
+    - 0.9
+    - 0.92
+    - 0.94
+    - 0.96
+    - 0.98
+    - 1.0
+    - 1.02
+    - 1.04
+    - 1.06
+    - 1.08
+    - 1.1
+    - 1.12
+    - 1.14
+    - 1.16
+    - 1.18
+    - 1.2
+    - 1.22
+    - 1.24
+    - 1.26
+    - 1.28
+    - 1.3
+    - 1.32
+    - 1.34
+    - 1.36
+    - 1.38
+    - 1.4
+    - 1.42
+    - 1.44
+    - 1.46
+    - 1.48
+    - 1.5
+    - 1.52
+    - 1.54
+    - 1.56
+    - 1.58
+    - 1.6
+    - 1.62
+    - 1.64
+    - 1.66
+    - 1.68
+    - 1.7
+    - 1.72
+    - 1.74
+    - 1.76
+    - 1.78
+    - 1.8
+    - 1.82
+    - 1.84
+    - 1.86
+    - 1.88
+    - 1.9
+    - 1.92
+    - 1.94
+    - 1.96
+    - 1.98
+    - 2.0
+    - 2.02
+    - 2.04
+    - 2.06
+    - 2.08
+    - 2.1
+    - 2.12
+    - 2.14
+    - 2.16
+    - 2.18
+    - 2.2
+    - 2.22
+    - 2.24
+    - 2.26
+    - 2.28
+    - 2.3
+    - 2.32
+    - 2.34
+    - 2.36
+    - 2.38
+    - 2.4
+    - 2.42
+    - 2.44
+    - 2.46
+    - 2.48
+    - 2.5
+    - 2.52
+    - 2.54
+    - 2.56
+    - 2.58
+    - 2.6
+    - 2.62
+    - 2.64
+    - 2.66
+    - 2.68
+    - 2.7
+    - 2.72
+    - 2.74
+    - 2.76
+    - 2.78
+    - 2.8
+    - 2.82
+    - 2.84
+    - 2.86
+    - 2.88
+    - 2.9
+    - 2.92
+    - 2.94
+    - 2.96
+    - 2.98
+eval:
+  n_episodes: 50
+  batch_size: 10
+  use_async_envs: false
+wandb:
+  enable: true
+  disable_artifact: false
+  project: insert
+  notes: ''
+fps: 50
+env:
+  name: aloha
+  task: AlohaInsertion-v0
+  state_dim: 14
+  action_dim: 14
+  fps: ${fps}
+  episode_length: 500
+  gym:
+    obs_type: pixels_agent_pos
+    render_mode: rgb_array
+override_dataset_stats:
+  observation.images.top:
+    mean:
+    - - - 0.485
+    - - - 0.456
+    - - - 0.406
+    std:
+    - - - 0.229
+    - - - 0.224
+    - - - 0.225
+policy:
+  name: dot
+  n_obs_steps: 3
+  train_horizon: 150
+  inference_horizon: 100
+  lookback_obs_steps: 30
+  lookback_aug: 5
+  input_shapes:
+    observation.images.top:
+    - 3
+    - 480
+    - 640
+    observation.state:
+    - ${env.state_dim}
+  output_shapes:
+    action:
+    - ${env.action_dim}
+  input_normalization_modes:
+    observation.images.top: mean_std
+    observation.state: min_max
+  output_normalization_modes:
+    action: min_max
+  vision_backbone: resnet18
+  pretrained_backbone_weights: ResNet18_Weights.IMAGENET1K_V1
+  rescale_shape:
+  - 480
+  - 640
+  lora_rank: 20
+  merge_lora: true
+  crop_scale: 0.8
+  state_noise: 0.01
+  noise_decay: 0.999995
+  pre_norm: true
+  dim_model: 128
+  n_heads: 8
+  dim_feedforward: 512
+  n_decoder_layers: 8
+  dropout: 0.1
+  alpha: 0.98
+  train_alpha: 0.99
+  predict_every_n: 1
+  return_every_n: 1

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706683a6b1c1c69f0b5cc577c9dcf08a8761ff30b1b25ab3511f7a0ab050ae5e
+size 56555664

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0d0e1c523e870ff2a57f9cd4823d07335973367c2e9e0ee71913b5894234e9
+size 202117