{
  "_name_or_path": "microsoft/resnet-50",
  "architectures": [
    "ResNetForImageClassification"
  ],
  "depths": [
    3,
    4,
    6,
    3
  ],
  "downsample_in_first_stage": false,
  "embedding_size": 64,
  "hidden_act": "relu",
  "hidden_sizes": [
    256,
    512,
    1024,
    2048
  ],
  "id2label": {
    "0": "T-shirt",
    "1": "Trouser",
    "2": "Pullover",
    "3": "Dress",
    "4": "Coat",
    "5": "Sandal",
    "6": "Shirt",
    "7": "Sneaker",
    "8": "Bag",
    "9": "Ankle-boot"
  },
  "label2id": {
    "Ankle-boot": 9,
    "Bag": 8,
    "Coat": 4,
    "Dress": 3,
    "Pullover": 2,
    "Sandal": 5,
    "Shirt": 6,
    "Sneaker": 7,
    "T-shirt": 0,
    "Trouser": 1
  },
  "layer_type": "bottleneck",
  "model_type": "resnet",
  "num_channels": 3,
  "output_hidden_states": true,
  "problem_type": "single_label_classification",
  "torch_dtype": "float32",
  "transformers_version": "4.21.0"
}