{ "architectures": [ "SwinForImageClassification" ], "attention_probs_dropout_prob": 0.0, "depths": [ 2, 2, 18, 2 ], "drop_path_rate": 0.1, "embed_dim": 128, "encoder_stride": 32, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 1024, "id2label": { "0": "aloo_gobi", "1": "biryani", "2": "carbonara", "3": "dosa", "4": "jalebi", "5": "lotus_root", "6": "mapo_tofu", "7": "miso", "8": "naan", "9": "pani_puri", "10": "pesto", "11": "pizza", "12": "polenta", "13": "ramen", "14": "roti", "15": "samosa", "16": "sashimi", "17": "spiced_mushroom", "18": "sushi", "19": "takoyaki", "20": "tiramisu", "21": "tripe", "22": "vada_pav", "23": "yam" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "aloo_gobi": 0, "biryani": 1, "carbonara": 2, "dosa": 3, "jalebi": 4, "lotus_root": 5, "mapo_tofu": 6, "miso": 7, "naan": 8, "pani_puri": 9, "pesto": 10, "pizza": 11, "polenta": 12, "ramen": 13, "roti": 14, "samosa": 15, "sashimi": 16, "spiced_mushroom": 17, "sushi": 18, "takoyaki": 19, "tiramisu": 20, "tripe": 21, "vada_pav": 22, "yam": 23 }, "layer_norm_eps": 1e-05, "mlp_ratio": 4.0, "model_type": "swin", "num_channels": 3, "num_heads": [ 4, 8, 16, 32 ], "num_layers": 4, "out_features": [ "stage4" ], "out_indices": [ 4 ], "patch_size": 4, "path_norm": true, "problem_type": "single_label_classification", "qkv_bias": true, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4" ], "torch_dtype": "float32", "transformers_version": "4.51.3", "use_absolute_embeddings": false, "window_size": 7 }