configs/train/v1.json

{
    "data": {
        "aspect_ratio_range": [0.5, 2.0],
        "area_range": [250000, 1000000],
        "clamp_max_depth": 1000.0,
        "center_augmentation": 0.5,
        "fov_range_absolute": [1, 179],
        "fov_range_relative": [0.01, 1.0],
        "image_augmentation": ["jittering", "jpeg_loss", "blurring"],
        "datasets": [ 
            {
                "name": "TartanAir",
                "path": "blobmnt/data_v3/TartanAir",
                "label_type": "synthetic",
                "index": ".index.txt",
                "depth": "depth.png",
                "weight": 4.8,
                "center_augmentation": 0.25,
                "fov_range_absolute": [30, 150],
                "fov_range_relative": [0.5, 1.0],
                "image_augmentation": ["jittering", "jpeg_loss", "blurring", "shot_noise"]
            }
        ]
    },
    "model_version": "v1",
    "model": {
        "encoder": "dinov2_vitl14",
        "remap_output": "exp",
        "intermediate_layers": 4,
        "dim_upsample": [256, 128, 64],
        "dim_times_res_block_hidden": 2,
        "num_res_blocks": 2,
        "num_tokens_range": [1200, 2500],
        "last_conv_channels": 32,
        "last_conv_size": 1
    },
    "optimizer": {
        "type": "AdamW",
        "params": [
            {"params": {"include": ["*"], "exclude": ["*backbone.*"]}, "lr": 1e-4},
            {"params": {"include": ["*backbone.*"]}, "lr": 1e-5}
        ]
    },
    "lr_scheduler": {
        "type": "SequentialLR",
        "params": {
            "schedulers": [
                {"type": "LambdaLR", "params": {"lr_lambda": ["1.0", "max(0.0, min(1.0, (epoch - 1000) / 1000))"]}},
                {"type": "StepLR", "params": {"step_size": 25000, "gamma": 0.5}}
            ],
            "milestones": [2000]
        }
    },
    "low_resolution_training_steps": 50000,
    "loss": {
        "invalid": {},
        "synthetic": {
            "global": {"function": "affine_invariant_global_loss", "weight": 1.0, "params": {"align_resolution": 32}},
            "patch_4": {"function": "affine_invariant_local_loss", "weight": 1.0, "params": {"level": 4, "align_resolution": 16, "num_patches": 16}},
            "patch_16": {"function": "affine_invariant_local_loss", "weight": 1.0, "params": {"level": 16, "align_resolution": 8, "num_patches": 256}},
            "patch_64": {"function": "affine_invariant_local_loss", "weight": 1.0, "params": {"level": 64, "align_resolution": 4, "num_patches": 4096}},
            "normal": {"function": "normal_loss", "weight": 1.0},
            "mask": {"function": "mask_l2_loss", "weight": 1.0}
        },
        "sfm": {
            "global": {"function": "affine_invariant_global_loss", "weight": 1.0, "params": {"align_resolution": 32}},
            "patch_4": {"function": "affine_invariant_local_loss", "weight": 1.0, "params": {"level": 4, "align_resolution": 16, "num_patches": 16}},
            "patch_16": {"function": "affine_invariant_local_loss", "weight": 1.0, "params": {"level": 16, "align_resolution": 8, "num_patches": 256}},
            "mask": {"function": "mask_l2_loss", "weight": 1.0}
        },
        "lidar": {
            "global": {"function": "affine_invariant_global_loss", "weight": 1.0, "params": {"align_resolution": 32}},
            "patch_4": {"function": "affine_invariant_local_loss", "weight": 1.0, "params": {"level": 4, "align_resolution": 16, "num_patches": 16}},
            "mask": {"function": "mask_l2_loss", "weight": 1.0}
        }
    }
}