config.json

{
  "_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": "book",
    "1": "drink",
    "2": "computer",
    "3": "before",
    "4": "go",
    "5": "who",
    "6": "candy",
    "7": "cousin",
    "8": "deaf",
    "9": "fine",
    "10": "help",
    "11": "no",
    "12": "thin",
    "13": "walk"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "before": 3,
    "book": 0,
    "candy": 6,
    "computer": 2,
    "cousin": 7,
    "deaf": 8,
    "drink": 1,
    "fine": 9,
    "go": 4,
    "help": 10,
    "no": 11,
    "thin": 12,
    "walk": 13,
    "who": 5
  },
  "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": "4.26.1",
  "tubelet_size": 2,
  "use_mean_pooling": false
}