{ "_name_or_path": "facebook/detr-resnet-50", "activation_dropout": 0.0, "activation_function": "relu", "architectures": [ "DetrModel" ], "attention_dropout": 0.0, "auxiliary_loss": false, "backbone": "resnet50", "backbone_config": null, "backbone_kwargs": null, "bbox_cost": 5, "bbox_loss_coefficient": 5, "class_cost": 1, "classifier_dropout": 0.0, "d_model": 256, "decoder_attention_heads": 8, "decoder_ffn_dim": 2048, "decoder_layerdrop": 0.0, "decoder_layers": 6, "dice_loss_coefficient": 1, "dilation": false, "dropout": 0.1, "encoder_attention_heads": 8, "encoder_ffn_dim": 2048, "encoder_layerdrop": 0.0, "encoder_layers": 6, "eos_coefficient": 0.1, "giou_cost": 2, "giou_loss_coefficient": 2, "id2label": [ "shirt, blouse", "top, t-shirt, sweatshirt", "sweater", "cardigan", "jacket", "vest", "pants", "shorts", "skirt", "coat", "dress", "jumpsuit", "cape", "glasses", "hat", "headband, head covering, hair accessory", "tie", "glove", "watch", "belt", "leg warmer", "tights, stockings", "sock", "shoe", "bag, wallet", "scarf", "umbrella", "hood", "collar", "lapel", "epaulette", "sleeve", "pocket", "neckline", "buckle", "zipper", "applique", "bead", "bow", "flower", "fringe", "ribbon", "rivet", "ruffle", "sequin", "tassel" ], "init_std": 0.02, "init_xavier_std": 1.0, "is_encoder_decoder": true, "label2id": { "applique": 36, "bag, wallet": 24, "bead": 37, "belt": 19, "bow": 38, "buckle": 34, "cape": 12, "cardigan": 3, "coat": 9, "collar": 28, "dress": 10, "epaulette": 30, "flower": 39, "fringe": 40, "glasses": 13, "glove": 17, "hat": 14, "headband, head covering, hair accessory": 15, "hood": 27, "jacket": 4, "jumpsuit": 11, "lapel": 29, "leg warmer": 20, "neckline": 33, "pants": 6, "pocket": 32, "ribbon": 41, "rivet": 42, "ruffle": 43, "scarf": 25, "sequin": 44, "shirt, blouse": 0, "shoe": 23, "shorts": 7, "skirt": 8, "sleeve": 31, "sock": 22, "sweater": 2, "tassel": 45, "tie": 16, "tights, stockings": 21, "top, t-shirt, sweatshirt": 1, "umbrella": 26, "vest": 5, "watch": 18, "zipper": 35 }, "mask_loss_coefficient": 1, "max_position_embeddings": 1024, "model_type": "detr", "num_channels": 3, "num_hidden_layers": 6, "num_queries": 100, "position_embedding_type": "sine", "scale_embedding": false, "torch_dtype": "float32", "transformers_version": "4.38.2", "use_pretrained_backbone": true, "use_timm_backbone": true }