{ "_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": "Bhujangasana", "1": "Dhanurasana", "2": "Head_To_Knee_Pose", "3": "Padmasana", "4": "Setubandhasana", "5": "Shavasana", "6": "Tadasana", "7": "Trikonasana", "8": "Virbhadrasana1", "9": "Vrikshasana" }, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "Bhujangasana": 0, "Dhanurasana": 1, "Head_To_Knee_Pose": 2, "Padmasana": 3, "Setubandhasana": 4, "Shavasana": 5, "Tadasana": 6, "Trikonasana": 7, "Virbhadrasana1": 8, "Vrikshasana": 9 }, "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": "4.41.1", "tubelet_size": 2, "use_mean_pooling": false }