fashionpedia / config.json
hackolite's picture
Upload YolosForObjectDetection
2693642
{
"_name_or_path": "valentinafeve/yolos-fashionpedia",
"architectures": [
"YolosForObjectDetection"
],
"attention_probs_dropout_prob": 0.0,
"auxiliary_loss": false,
"bbox_cost": 5,
"bbox_loss_coefficient": 5,
"class_cost": 1,
"eos_coefficient": 0.1,
"giou_cost": 2,
"giou_loss_coefficient": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 384,
"id2label": {
"0": "shirt, blouse",
"1": "top, t-shirt, sweatshirt",
"2": "sweater",
"3": "cardigan",
"4": "jacket",
"5": "vest",
"6": "pants",
"7": "shorts",
"8": "skirt",
"9": "coat",
"10": "dress",
"11": "jumpsuit",
"12": "cape",
"13": "glasses",
"14": "hat",
"15": "headband, head covering, hair accessory",
"16": "tie",
"17": "glove",
"18": "watch",
"19": "belt",
"20": "leg warmer",
"21": "tights, stockings",
"22": "sock",
"23": "shoe",
"24": "bag, wallet",
"25": "scarf",
"26": "umbrella",
"27": "hood",
"28": "collar",
"29": "lapel",
"30": "epaulette",
"31": "sleeve",
"32": "pocket",
"33": "neckline",
"34": "buckle",
"35": "zipper",
"36": "applique",
"37": "bead",
"38": "bow",
"39": "flower",
"40": "fringe",
"41": "ribbon",
"42": "rivet",
"43": "ruffle",
"44": "sequin",
"45": "tassel"
},
"image_size": [
512,
864
],
"initializer_range": 0.02,
"intermediate_size": 1536,
"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
},
"layer_norm_eps": 1e-12,
"model_type": "yolos",
"num_attention_heads": 6,
"num_channels": 3,
"num_detection_tokens": 100,
"num_hidden_layers": 12,
"patch_size": 16,
"qkv_bias": true,
"torch_dtype": "float32",
"transformers_version": "4.23.1",
"use_mid_position_embeddings": true
}