config.json

{
  "beta_end": 0.02,
  "beta_schedule": "squaredcos_cap_v2",
  "beta_start": 0.0001,
  "clip_sample": true,
  "clip_sample_range": 1.0,
  "crop_is_random": true,
  "crop_shape": [
    84,
    84
  ],
  "diffusion_step_embed_dim": 128,
  "do_mask_loss_for_padding": false,
  "down_dims": [
    512,
    1024,
    2048
  ],
  "drop_n_last_frames": 7,
  "horizon": 16,
  "input_features": {
    "observation.image": {
      "shape": [
        3,
        96,
        96
      ],
      "type": "VISUAL"
    },
    "observation.state": {
      "shape": [
        2
      ],
      "type": "STATE"
    }
  },
  "kernel_size": 5,
  "n_action_steps": 8,
  "n_groups": 8,
  "n_obs_steps": 2,
  "noise_scheduler_type": "DDPM",
  "normalization_mapping": {
    "ACTION": "MIN_MAX",
    "STATE": "MIN_MAX",
    "VISUAL": "MEAN_STD"
  },
  "num_inference_steps": null,
  "num_train_timesteps": 100,
  "optimizer_betas": [
    0.95,
    0.999
  ],
  "optimizer_eps": 1e-08,
  "optimizer_lr": 0.0001,
  "optimizer_weight_decay": 1e-06,
  "output_features": {
    "action": {
      "shape": [
        2
      ],
      "type": "ACTION"
    }
  },
  "prediction_type": "epsilon",
  "pretrained_backbone_weights": null,
  "scheduler_name": "cosine",
  "scheduler_warmup_steps": 500,
  "spatial_softmax_num_keypoints": 32,
  "type": "diffusion",
  "use_film_scale_modulation": true,
  "use_group_norm": true,
  "use_separate_rgb_encoder_per_camera": false,
  "vision_backbone": "resnet18"
}