{ "_name_or_path": "nvidia/mit-b2", "architectures": [ "SegformerForSemanticSegmentation" ], "attention_probs_dropout_prob": 0.0, "classifier_dropout_prob": 0.1, "decoder_hidden_size": 768, "depths": [ 3, 4, 6, 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": "Everything Else", "1": "shirt, blouse", "2": "top, t-shirt, sweatshirt", "3": "sweater", "4": "cardigan", "5": "jacket", "6": "vest", "7": "pants", "8": "shorts", "9": "skirt", "10": "coat", "11": "dress", "12": "jumpsuit", "13": "cape", "14": "glasses", "15": "hat", "16": "headband, head covering, hair accessory", "17": "tie", "18": "glove", "19": "watch", "20": "belt", "21": "leg warmer", "22": "tights, stockings", "23": "sock", "24": "shoe", "25": "bag, wallet", "26": "scarf", "27": "umbrella", "28": "hood", "29": "collar", "30": "lapel", "31": "epaulette", "32": "sleeve", "33": "pocket", "34": "neckline", "35": "buckle", "36": "zipper", "37": "applique", "38": "bead", "39": "bow", "40": "flower", "41": "fringe", "42": "ribbon", "43": "rivet", "44": "ruffle", "45": "sequin", "46": "tassel" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "Everything Else": 0, "applique": 37, "bag, wallet": 25, "bead": 38, "belt": 20, "bow": 39, "buckle": 35, "cape": 13, "cardigan": 4, "coat": 10, "collar": 29, "dress": 11, "epaulette": 31, "flower": 40, "fringe": 41, "glasses": 14, "glove": 18, "hat": 15, "headband, head covering, hair accessory": 16, "hood": 28, "jacket": 5, "jumpsuit": 12, "lapel": 30, "leg warmer": 21, "neckline": 34, "pants": 7, "pocket": 33, "ribbon": 42, "rivet": 43, "ruffle": 44, "scarf": 26, "sequin": 45, "shirt, blouse": 1, "shoe": 24, "shorts": 8, "skirt": 9, "sleeve": 32, "sock": 23, "sweater": 3, "tassel": 46, "tie": 17, "tights, stockings": 22, "top, t-shirt, sweatshirt": 2, "umbrella": 27, "vest": 6, "watch": 19, "zipper": 36 }, "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 ], "torch_dtype": "float32", "transformers_version": "4.30.0" }