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": "Normal Forward Driving",
    "1": "Drinking",
    "2": "Phone Call(right)",
    "3": "Phone Call(left)",
    "4": "Eating",
    "5": "Text (Right)",
    "6": "Text (Left)",
    "7": "Reaching behind",
    "8": "Adjust control panel",
    "9": "Pick up from floor (Driver)",
    "10": "Pick up from floor (Passenger)",
    "11": "Talk to passenger at the right",
    "12": "Talk to passenger at backseat",
    "13": "yawning",
    "14": "Hand on head",
    "15": "Singing or dancing with music"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Adjust control panel": 8,
    "Drinking": 1,
    "Eating": 4,
    "Hand on head": 14,
    "Normal Forward Driving": 0,
    "Phone Call(left)": 3,
    "Phone Call(right)": 2,
    "Pick up from floor (Driver)": 9,
    "Pick up from floor (Passenger)": 10,
    "Reaching behind": 7,
    "Singing or dancing with music": 15,
    "Talk to passenger at backseat": 12,
    "Talk to passenger at the right": 11,
    "Text (Left)": 6,
    "Text (Right)": 5,
    "yawning": 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": "4.35.2",
  "tubelet_size": 2,
  "use_mean_pooling": false
}