File size: 1,648 Bytes
23ecfd3 |
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 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
{
"_name_or_path": "facebook/dinov2-base",
"apply_layernorm": true,
"architectures": [
"Dinov2ForImageClassification"
],
"attention_probs_dropout_prob": 0.0,
"drop_path_rate": 0.0,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 768,
"id2label": {
"0": "calling",
"1": "clapping",
"2": "cycling",
"3": "dancing",
"4": "drinking",
"5": "eating",
"6": "fighting",
"7": "hugging",
"8": "laughing",
"9": "listening_to_music",
"10": "running",
"11": "sitting",
"12": "sleeping",
"13": "texting",
"14": "using_laptop"
},
"image_size": 518,
"initializer_range": 0.02,
"label2id": {
"calling": 0,
"clapping": 1,
"cycling": 2,
"dancing": 3,
"drinking": 4,
"eating": 5,
"fighting": 6,
"hugging": 7,
"laughing": 8,
"listening_to_music": 9,
"running": 10,
"sitting": 11,
"sleeping": 12,
"texting": 13,
"using_laptop": 14
},
"layer_norm_eps": 1e-06,
"layerscale_value": 1.0,
"mlp_ratio": 4,
"model_type": "dinov2",
"num_attention_heads": 12,
"num_channels": 3,
"num_hidden_layers": 12,
"out_features": [
"stage12"
],
"out_indices": [
12
],
"patch_size": 14,
"problem_type": "single_label_classification",
"qkv_bias": true,
"reshape_hidden_states": true,
"stage_names": [
"stem",
"stage1",
"stage2",
"stage3",
"stage4",
"stage5",
"stage6",
"stage7",
"stage8",
"stage9",
"stage10",
"stage11",
"stage12"
],
"torch_dtype": "float32",
"transformers_version": "4.44.0",
"use_swiglu_ffn": false
}
|