flatala-research's picture
Training in progress, epoch 0
61636e1 verified
{
"_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
"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": "DOWN",
"1": "FOREWARD",
"2": "LEFT",
"3": "NO_MOVEMENT",
"4": "RIGHT",
"5": "ROTATION",
"6": "SELF",
"7": "UP"
},
"image_size": 224,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"DOWN": 0,
"FOREWARD": 1,
"LEFT": 2,
"NO_MOVEMENT": 3,
"RIGHT": 4,
"ROTATION": 5,
"SELF": 6,
"UP": 7
},
"layer_norm_eps": 1e-12,
"model_type": "videomae",
"norm_pix_loss": false,
"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": "4.41.0",
"tubelet_size": 2,
"use_mean_pooling": true
}