{ "architectures": [ "ConvNextForImageClassification" ], "attention_probs_dropout_prob": 0.0, "depths": [ 3, 3, 9, 3 ], "drop_path_rate": 0.0, "encoder_stride": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "hidden_sizes": [ 96, 192, 384, 768 ], "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3" }, "image_size": 512, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3 }, "layer_norm_eps": 1e-12, "layer_scale_init_value": 1e-06, "model_type": "convnext", "num_attention_heads": 12, "num_channels": 1, "num_hidden_layers": 12, "num_stages": 4, "patch_size": 16, "problem_type": "single_label_classification", "qkv_bias": true, "torch_dtype": "float32", "transformers_version": "4.20.1" }