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": "blowing nose",
    "1": "brushing teeth",
    "2": "crying",
    "3": "drinking shots",
    "4": "eating chips",
    "5": "laughing",
    "6": "sipping cup",
    "7": "sleeping",
    "8": "smoking",
    "9": "sneezing",
    "10": "talking on cell phone",
    "11": "texting",
    "12": "throwing tantrum",
    "13": "using inhaler",
    "14": "waking up",
    "15": "watching tv"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "blowing nose": 0,
    "brushing teeth": 1,
    "crying": 2,
    "drinking shots": 3,
    "eating chips": 4,
    "laughing": 5,
    "sipping cup": 6,
    "sleeping": 7,
    "smoking": 8,
    "sneezing": 9,
    "talking on cell phone": 10,
    "texting": 11,
    "throwing tantrum": 12,
    "using inhaler": 13,
    "waking up": 14,
    "watching tv": 15
  },
  "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": "4.43.4",
  "tubelet_size": 2,
  "use_mean_pooling": false
}