{ "architectures": [ "VitPoseForPoseEstimation" ], "backbone": null, "backbone_config": { "attention_probs_dropout_prob": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 384, "image_size": [ 256, 192 ], "initializer_range": 0.02, "layer_norm_eps": 1e-12, "mlp_ratio": 4, "model_type": "vitpose_backbone", "num_attention_heads": 12, "num_channels": 3, "num_experts": 6, "num_hidden_layers": 12, "out_features": [ "stage12" ], "out_indices": [ 12 ], "part_features": 96, "patch_size": [ 16, 16 ], "qkv_bias": true, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4", "stage5", "stage6", "stage7", "stage8", "stage9", "stage10", "stage11", "stage12" ] }, "backbone_kwargs": null, "dtype": "float32", "edges": [ [ 15, 13 ], [ 13, 11 ], [ 16, 14 ], [ 14, 12 ], [ 11, 12 ], [ 5, 11 ], [ 6, 12 ], [ 5, 6 ], [ 5, 7 ], [ 6, 8 ], [ 7, 9 ], [ 8, 10 ], [ 1, 2 ], [ 0, 1 ], [ 0, 2 ], [ 1, 3 ], [ 2, 4 ], [ 3, 5 ], [ 4, 6 ] ], "edges_per_dataset": null, "flip_pairs_per_dataset": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7", "8": "LABEL_8", "9": "LABEL_9", "10": "LABEL_10", "11": "LABEL_11", "12": "LABEL_12", "13": "LABEL_13", "14": "LABEL_14", "15": "LABEL_15", "16": "LABEL_16" }, "id2label_per_dataset": null, "initializer_range": 0.02, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_10": 10, "LABEL_11": 11, "LABEL_12": 12, "LABEL_13": 13, "LABEL_14": 14, "LABEL_15": 15, "LABEL_16": 16, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7, "LABEL_8": 8, "LABEL_9": 9 }, "model_type": "vitpose", "num_labels_per_dataset": [ 17, 14, 16, 17, 17, 133 ], "scale_factor": 4, "transformers_version": "5.0.0.dev0", "use_pretrained_backbone": false, "use_simple_decoder": false, "use_timm_backbone": false }