File size: 1,253 Bytes
34861f4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
{
"_name_or_path": "google/vit-base-patch16-224",
"architectures": [
"ViTForImageClassification"
],
"attention_probs_dropout_prob": 0.0,
"encoder_stride": 16,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 768,
"id2label": {
"0": "Abuse",
"1": "Arrest",
"10": "Shooting",
"11": "Shoplifting",
"12": "Stealing",
"13": "Vandalism",
"2": "Arson",
"3": "Assault",
"4": "Burglary",
"5": "Explosion",
"6": "Fighting",
"7": "NormalVideos",
"8": "RoadAccidents",
"9": "Robbery"
},
"image_size": 224,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Abuse": "0",
"Arrest": "1",
"Arson": "2",
"Assault": "3",
"Burglary": "4",
"Explosion": "5",
"Fighting": "6",
"NormalVideos": "7",
"RoadAccidents": "8",
"Robbery": "9",
"Shooting": "10",
"Shoplifting": "11",
"Stealing": "12",
"Vandalism": "13"
},
"layer_norm_eps": 1e-12,
"model_type": "vit",
"num_attention_heads": 12,
"num_channels": 3,
"num_hidden_layers": 12,
"patch_size": 16,
"problem_type": "single_label_classification",
"qkv_bias": true,
"torch_dtype": "float32",
"transformers_version": "4.21.1"
}
|