{ | |
"architectures": [ | |
"ViTForImageClassification" | |
], | |
"attention_probs_dropout_prob": 0.0, | |
"encoder_stride": 16, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.0, | |
"hidden_size": 768, | |
"id2label": { | |
"0": "CANDY", | |
"1": "CHIPS", | |
"2": "CHOCOLATE", | |
"3": "FISH", | |
"4": "JAM", | |
"5": "MILK", | |
"6": "OIL", | |
"7": "SPICES", | |
"8": "TOMATO_SAUCE", | |
"9": "WATER" | |
}, | |
"image_size": 224, | |
"initializer_range": 0.02, | |
"intermediate_size": 3072, | |
"label2id": { | |
"CANDY": "0", | |
"CHIPS": "1", | |
"CHOCOLATE": "2", | |
"FISH": "3", | |
"JAM": "4", | |
"MILK": "5", | |
"OIL": "6", | |
"SPICES": "7", | |
"TOMATO_SAUCE": "8", | |
"WATER": "9" | |
}, | |
"layer_norm_eps": 1e-12, | |
"model_type": "vit", | |
"num_attention_heads": 12, | |
"num_channels": 3, | |
"num_hidden_layers": 12, | |
"patch_size": 16, | |
"pooler_act": "tanh", | |
"pooler_output_size": 768, | |
"problem_type": "single_label_classification", | |
"qkv_bias": true, | |
"torch_dtype": "float32", | |
"transformers_version": "4.51.3" | |
} | |