codeby-hp/finetune-VIT-HumanPoseClassification

1{2  "architectures": [3    "ViTForImageClassification"4  ],5  "attention_probs_dropout_prob": 0.0,6  "dtype": "float32",7  "encoder_stride": 16,8  "hidden_act": "gelu",9  "hidden_dropout_prob": 0.0,10  "hidden_size": 768,11  "id2label": {12    "0": "calling",13    "1": "clapping",14    "2": "cycling",15    "3": "dancing",16    "4": "drinking",17    "5": "eating",18    "6": "fighting",19    "7": "hugging",20    "8": "laughing",21    "9": "listening_to_music",22    "10": "running",23    "11": "sitting",24    "12": "sleeping",25    "13": "texting",26    "14": "using_laptop"27  },28  "image_size": 224,29  "initializer_range": 0.02,30  "intermediate_size": 3072,31  "label2id": {32    "calling": 0,33    "clapping": 1,34    "cycling": 2,35    "dancing": 3,36    "drinking": 4,37    "eating": 5,38    "fighting": 6,39    "hugging": 7,40    "laughing": 8,41    "listening_to_music": 9,42    "running": 10,43    "sitting": 11,44    "sleeping": 12,45    "texting": 13,46    "using_laptop": 1447  },48  "layer_norm_eps": 1e-12,49  "model_type": "vit",50  "num_attention_heads": 12,51  "num_channels": 3,52  "num_hidden_layers": 12,53  "patch_size": 16,54  "pooler_act": "tanh",55  "pooler_output_size": 768,56  "problem_type": "single_label_classification",57  "qkv_bias": true,58  "transformers_version": "4.57.3"59}60