|
{ |
|
"_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": "01", |
|
"1": "02", |
|
"2": "03", |
|
"3": "04", |
|
"4": "05", |
|
"5": "06", |
|
"6": "07", |
|
"7": "08", |
|
"8": "09", |
|
"9": "10", |
|
"10": "11", |
|
"11": "13", |
|
"12": "14", |
|
"13": "15", |
|
"14": "16", |
|
"15": "17", |
|
"16": "18", |
|
"17": "20", |
|
"18": "21", |
|
"19": "22", |
|
"20": "23", |
|
"21": "24", |
|
"22": "25", |
|
"23": "26", |
|
"24": "27", |
|
"25": "29", |
|
"26": "30", |
|
"27": "31", |
|
"28": "32", |
|
"29": "34", |
|
"30": "36", |
|
"31": "37", |
|
"32": "38", |
|
"33": "39", |
|
"34": "40", |
|
"35": "41", |
|
"36": "42", |
|
"37": "43", |
|
"38": "44", |
|
"39": "47", |
|
"40": "48", |
|
"41": "49", |
|
"42": "50", |
|
"43": "51", |
|
"44": "52", |
|
"45": "54", |
|
"46": "55", |
|
"47": "56", |
|
"48": "57", |
|
"49": "58", |
|
"50": "59", |
|
"51": "60", |
|
"52": "61", |
|
"53": "62", |
|
"54": "63", |
|
"55": "64", |
|
"56": "65", |
|
"57": "66", |
|
"58": "67", |
|
"59": "68", |
|
"60": "69", |
|
"61": "70", |
|
"62": "71", |
|
"63": "72", |
|
"64": "74", |
|
"65": "76", |
|
"66": "77" |
|
}, |
|
"image_size": 224, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"01": 0, |
|
"02": 1, |
|
"03": 2, |
|
"04": 3, |
|
"05": 4, |
|
"06": 5, |
|
"07": 6, |
|
"08": 7, |
|
"09": 8, |
|
"10": 9, |
|
"11": 10, |
|
"13": 11, |
|
"14": 12, |
|
"15": 13, |
|
"16": 14, |
|
"17": 15, |
|
"18": 16, |
|
"20": 17, |
|
"21": 18, |
|
"22": 19, |
|
"23": 20, |
|
"24": 21, |
|
"25": 22, |
|
"26": 23, |
|
"27": 24, |
|
"29": 25, |
|
"30": 26, |
|
"31": 27, |
|
"32": 28, |
|
"34": 29, |
|
"36": 30, |
|
"37": 31, |
|
"38": 32, |
|
"39": 33, |
|
"40": 34, |
|
"41": 35, |
|
"42": 36, |
|
"43": 37, |
|
"44": 38, |
|
"47": 39, |
|
"48": 40, |
|
"49": 41, |
|
"50": 42, |
|
"51": 43, |
|
"52": 44, |
|
"54": 45, |
|
"55": 46, |
|
"56": 47, |
|
"57": 48, |
|
"58": 49, |
|
"59": 50, |
|
"60": 51, |
|
"61": 52, |
|
"62": 53, |
|
"63": 54, |
|
"64": 55, |
|
"65": 56, |
|
"66": 57, |
|
"67": 58, |
|
"68": 59, |
|
"69": 60, |
|
"70": 61, |
|
"71": 62, |
|
"72": 63, |
|
"74": 64, |
|
"76": 65, |
|
"77": 66 |
|
}, |
|
"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": "4.48.0", |
|
"tubelet_size": 2, |
|
"use_mean_pooling": false |
|
} |
|
|