{
  "model_type": "image_feature_extractor_cnn",
  "torch_dtype": "float32",
  "in_channels": 3,
  "image_size": 224,
  "embed_dim": 256,
  "base_channels": 32,
  "num_blocks": 4,
  "dropout": 0.0,
  "pool": "avg",
  "norm": "bn",
  "task": "feature_extraction",
  "outputs": {
    "embedding": "float32[batch, embed_dim]"
  },
  "preprocessing": {
    "expected_input": "float32 images in [0,1] normalized",
    "suggested_normalize": {
      "mean": [
        0.485,
        0.456,
        0.406
      ],
      "std": [
        0.229,
        0.224,
        0.225
      ]
    },
    "resize": 224
  },
  "id2label": null,
  "label2id": null,
  "version": "0.1.0"
}