80videomae / config.json
rish13's picture
Upload VideoMAEForVideoClassification
3af60e6 verified
{
"_name_or_path": "MCG-NJU/videomae-base",
"architectures": [
"VideoMAEForVideoClassification"
],
"attention_probs_dropout_prob": 0.0,
"decoder_hidden_size": 384,
"decoder_intermediate_size": 1536,
"decoder_num_attention_heads": 6,
"decoder_num_hidden_layers": 4,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 768,
"id2label": {
"0": "abuse",
"1": "arrest",
"2": "arson",
"3": "assault",
"4": "burglary",
"5": "explosion",
"6": "fighting",
"7": "normal",
"8": "roadaccidents",
"9": "robbery",
"10": "shooting",
"11": "shoplifting",
"12": "stealing",
"13": "vandalism"
},
"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,
"normal": 7,
"roadaccidents": 8,
"robbery": 9,
"shooting": 10,
"shoplifting": 11,
"stealing": 12,
"vandalism": 13
},
"layer_norm_eps": 1e-12,
"model_type": "videomae",
"norm_pix_loss": true,
"num_attention_heads": 12,
"num_channels": 3,
"num_frames": 16,
"num_hidden_layers": 12,
"patch_size": 16,
"problem_type": "single_label_classification",
"qkv_bias": true,
"torch_dtype": "float32",
"transformers_version": "4.46.2",
"tubelet_size": 2,
"use_mean_pooling": false
}