{
    "type": "act",
    "n_obs_steps": 1,
    "normalization_mapping": {
        "VISUAL": "IDENTITY",
        "STATE": "MEAN_STD",
        "ACTION": "MEAN_STD"
    },
    "input_features": {
        "observation.state": {
            "type": "STATE",
            "shape": [
                7
            ]
        },
        "observation.images.wrist": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        },
        "observation.images.webcam": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        }
    },
    "output_features": {
        "action": {
            "type": "ACTION",
            "shape": [
                7
            ]
        }
    },
    "device": "cuda",
    "use_amp": false,
    "chunk_size": 100,
    "n_action_steps": 100,
    "vision_backbone": "ProtoSAM",
    "pretrained_backbone_weights": "weights/FastSAM-s.pt",
    "proto_indices": [
        3,
        5,
        6,
        8,
        19,
        31,
        21
    ],
    "freeze_backbone": true,
    "replace_final_stride_with_dilation": false,
    "pre_norm": false,
    "dim_model": 448,
    "n_heads": 8,
    "dim_feedforward": 3200,
    "feedforward_activation": "relu",
    "n_encoder_layers": 4,
    "n_decoder_layers": 1,
    "use_vae": true,
    "latent_dim": 32,
    "n_vae_encoder_layers": 4,
    "use_depth_transform": false,
    "temporal_ensemble_coeff": null,
    "dropout": 0.1,
    "kl_weight": 10.0,
    "optimizer_lr": 1e-05,
    "optimizer_weight_decay": 0.0001,
    "optimizer_lr_backbone": 1e-05
}