| { | |
| "_name_or_path": "jonathandinu/face-parsing", | |
| "architectures": [ | |
| "SegformerForSemanticSegmentation" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "classifier_dropout_prob": 0.1, | |
| "decoder_hidden_size": 768, | |
| "depths": [ | |
| 3, | |
| 6, | |
| 40, | |
| 3 | |
| ], | |
| "downsampling_rates": [ | |
| 1, | |
| 4, | |
| 8, | |
| 16 | |
| ], | |
| "drop_path_rate": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_sizes": [ | |
| 64, | |
| 128, | |
| 320, | |
| 512 | |
| ], | |
| "id2label": { | |
| "0": "background", | |
| "1": "skin", | |
| "2": "nose", | |
| "3": "eye_g", | |
| "4": "l_eye", | |
| "5": "r_eye", | |
| "6": "l_brow", | |
| "7": "r_brow", | |
| "8": "l_ear", | |
| "9": "r_ear", | |
| "10": "mouth", | |
| "11": "u_lip", | |
| "12": "l_lip", | |
| "13": "hair", | |
| "14": "hat", | |
| "15": "ear_r", | |
| "16": "neck_l", | |
| "17": "neck", | |
| "18": "cloth" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "background": 0, | |
| "skin": 1, | |
| "nose": 2, | |
| "eye_g": 3, | |
| "l_eye": 4, | |
| "r_eye": 5, | |
| "l_brow": 6, | |
| "r_brow": 7, | |
| "l_ear": 8, | |
| "r_ear": 9, | |
| "mouth": 10, | |
| "u_lip": 11, | |
| "l_lip": 12, | |
| "hair": 13, | |
| "hat": 14, | |
| "ear_r": 15, | |
| "neck_l": 16, | |
| "neck": 17, | |
| "cloth": 18 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "mlp_ratios": [ | |
| 4, | |
| 4, | |
| 4, | |
| 4 | |
| ], | |
| "model_type": "segformer", | |
| "num_attention_heads": [ | |
| 1, | |
| 2, | |
| 5, | |
| 8 | |
| ], | |
| "num_channels": 3, | |
| "num_encoder_blocks": 4, | |
| "patch_sizes": [ | |
| 7, | |
| 3, | |
| 3, | |
| 3 | |
| ], | |
| "reshape_last_stage": true, | |
| "semantic_loss_ignore_index": 255, | |
| "sr_ratios": [ | |
| 8, | |
| 4, | |
| 2, | |
| 1 | |
| ], | |
| "strides": [ | |
| 4, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "transformers_version": "4.37.0.dev0" | |
| } | |