{
    "lightning_module": "VelocityEstimatorModel",
    "total_parameters": 25065794,
    "trainable_parameters": 441601,
    "model_structure": "VelocityEstimatorModel(\n  (model): VelocityNetwork(\n    (image_encoder): VelocityNetwork(\n      (backbone): Sequential(\n        (0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n        (2): ReLU(inplace=True)\n        (3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n        (4): Sequential(\n          (0): Bottleneck(\n            (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n            (downsample): Sequential(\n              (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n              (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            )\n          )\n          (1): Bottleneck(\n            (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (2): Bottleneck(\n            (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n        )\n        (5): Sequential(\n          (0): Bottleneck(\n            (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n            (downsample): Sequential(\n              (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n              (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            )\n          )\n          (1): Bottleneck(\n            (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (2): Bottleneck(\n            (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (3): Bottleneck(\n            (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n        )\n        (6): Sequential(\n          (0): Bottleneck(\n            (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n            (downsample): Sequential(\n              (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n              (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            )\n          )\n          (1): Bottleneck(\n            (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (2): Bottleneck(\n            (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (3): Bottleneck(\n            (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (4): Bottleneck(\n            (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (5): Bottleneck(\n            (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n        )\n        (7): Sequential(\n          (0): Bottleneck(\n            (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n            (downsample): Sequential(\n              (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n              (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            )\n          )\n          (1): Bottleneck(\n            (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n          (2): Bottleneck(\n            (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n            (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n            (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n            (relu): ReLU(inplace=True)\n          )\n        )\n        (8): AdaptiveAvgPool2d(output_size=(1, 1))\n      )\n      (embedding_head): Sequential(\n        (0): Linear(in_features=2048, out_features=512, bias=True)\n        (1): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n        (2): GELU(approximate='none')\n        (3): Dropout(p=0.3, inplace=False)\n      )\n      (regression_head): Sequential(\n        (0): Linear(in_features=512, out_features=128, bias=True)\n        (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n        (2): GELU(approximate='none')\n        (3): Dropout(p=0.2, inplace=False)\n        (4): Linear(in_features=128, out_features=1, bias=True)\n      )\n    )\n    (regressor): Sequential(\n      (0): Linear(in_features=521, out_features=512, bias=True)\n      (1): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n      (2): GELU(approximate='none')\n      (3): Dropout(p=0.2, inplace=False)\n      (4): Linear(in_features=512, out_features=256, bias=True)\n      (5): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n      (6): GELU(approximate='none')\n      (7): Dropout(p=0.2, inplace=False)\n      (8): Linear(in_features=256, out_features=128, bias=True)\n      (9): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, bias=True, track_running_stats=True)\n      (10): GELU(approximate='none')\n      (11): Linear(in_features=128, out_features=64, bias=True)\n      (12): GELU(approximate='none')\n      (13): Linear(in_features=64, out_features=1, bias=True)\n    )\n  )\n  (train_mae): MeanAbsoluteError()\n  (val_mae): MeanAbsoluteError()\n  (test_mae): MeanAbsoluteError()\n)"
}