{ | |
"_name_or_path": "google/vivit-b-16x2-kinetics400", | |
"architectures": [ | |
"VivitForVideoClassification" | |
], | |
"attention_probs_dropout_prob": 0.0, | |
"hidden_act": "gelu_fast", | |
"hidden_dropout_prob": 0.0, | |
"hidden_size": 768, | |
"id2label": { | |
"0": "LABEL_0", | |
"1": "LABEL_1", | |
"2": "LABEL_2", | |
"3": "LABEL_3", | |
"4": "LABEL_4", | |
"5": "LABEL_5", | |
"6": "LABEL_6", | |
"7": "LABEL_7", | |
"8": "LABEL_8", | |
"9": "LABEL_9", | |
"10": "LABEL_10", | |
"11": "LABEL_11", | |
"12": "LABEL_12", | |
"13": "LABEL_13", | |
"14": "LABEL_14", | |
"15": "LABEL_15", | |
"16": "LABEL_16", | |
"17": "LABEL_17", | |
"18": "LABEL_18", | |
"19": "LABEL_19", | |
"20": "LABEL_20", | |
"21": "LABEL_21", | |
"22": "LABEL_22", | |
"23": "LABEL_23", | |
"24": "LABEL_24", | |
"25": "LABEL_25", | |
"26": "LABEL_26", | |
"27": "LABEL_27", | |
"28": "LABEL_28", | |
"29": "LABEL_29", | |
"30": "LABEL_30", | |
"31": "LABEL_31", | |
"32": "LABEL_32", | |
"33": "LABEL_33", | |
"34": "LABEL_34", | |
"35": "LABEL_35", | |
"36": "LABEL_36", | |
"37": "LABEL_37", | |
"38": "LABEL_38", | |
"39": "LABEL_39" | |
}, | |
"image_size": 224, | |
"initializer_range": 0.02, | |
"intermediate_size": 3072, | |
"label2id": { | |
"LABEL_0": 0, | |
"LABEL_1": 1, | |
"LABEL_10": 10, | |
"LABEL_11": 11, | |
"LABEL_12": 12, | |
"LABEL_13": 13, | |
"LABEL_14": 14, | |
"LABEL_15": 15, | |
"LABEL_16": 16, | |
"LABEL_17": 17, | |
"LABEL_18": 18, | |
"LABEL_19": 19, | |
"LABEL_2": 2, | |
"LABEL_20": 20, | |
"LABEL_21": 21, | |
"LABEL_22": 22, | |
"LABEL_23": 23, | |
"LABEL_24": 24, | |
"LABEL_25": 25, | |
"LABEL_26": 26, | |
"LABEL_27": 27, | |
"LABEL_28": 28, | |
"LABEL_29": 29, | |
"LABEL_3": 3, | |
"LABEL_30": 30, | |
"LABEL_31": 31, | |
"LABEL_32": 32, | |
"LABEL_33": 33, | |
"LABEL_34": 34, | |
"LABEL_35": 35, | |
"LABEL_36": 36, | |
"LABEL_37": 37, | |
"LABEL_38": 38, | |
"LABEL_39": 39, | |
"LABEL_4": 4, | |
"LABEL_5": 5, | |
"LABEL_6": 6, | |
"LABEL_7": 7, | |
"LABEL_8": 8, | |
"LABEL_9": 9 | |
}, | |
"layer_norm_eps": 1e-06, | |
"model_type": "vivit", | |
"num_attention_heads": 12, | |
"num_channels": 3, | |
"num_frames": 32, | |
"num_hidden_layers": 12, | |
"problem_type": "multi_label_classification", | |
"qkv_bias": true, | |
"torch_dtype": "float32", | |
"transformers_version": "4.35.2", | |
"tubelet_size": [ | |
2, | |
16, | |
16 | |
], | |
"video_size": [ | |
32, | |
224, | |
224 | |
] | |
} | |