--- license: apache-2.0 language: - en base_model: - google/siglip2-base-patch16-224 pipeline_tag: image-classification library_name: transformers tags: - fashion - articleType - product - siglip2 --- ![17.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/dHy-iubqlC4_rsb6xWAl-.png) # **Fashion-Product-articleType** > **Fashion-Product-articleType** is a vision model fine-tuned from **google/siglip2-base-patch16-224** using the **SiglipForImageClassification** architecture. It classifies fashion product images into one of 141 article types. ```py Classification Report: precision recall f1-score support Accessory Gift Set 0.9898 1.0000 0.9949 97 Baby Dolls 0.6667 0.1429 0.2353 14 Backpacks 0.9582 0.9503 0.9542 724 Bangle 0.8421 0.7529 0.7950 85 Basketballs 0.7500 0.9231 0.8276 13 Bath Robe 0.8571 0.7059 0.7742 17 Beauty Accessory 0.0000 0.0000 0.0000 3 Belts 0.9842 0.9938 0.9890 813 Blazers 0.8333 0.6250 0.7143 8 Body Lotion 1.0000 0.3333 0.5000 3 Body Wash and Scrub 0.0000 0.0000 0.0000 1 Booties 0.6875 0.9167 0.7857 12 Boxers 0.8679 0.8846 0.8762 52 Bra 0.9614 0.9916 0.9763 477 Bracelet 0.7656 0.7424 0.7538 66 Briefs 0.9731 0.9811 0.9771 847 Camisoles 0.7500 0.5385 0.6269 39 Capris 0.6558 0.8057 0.7231 175 Caps 0.9317 0.9647 0.9479 283 Casual Shoes 0.8338 0.8643 0.8488 2845 Churidar 0.7500 0.5000 0.6000 30 Clothing Set 0.7500 0.3750 0.5000 8 Clutches 0.8015 0.7431 0.7712 288 Compact 0.8864 1.0000 0.9398 39 Concealer 0.7143 0.9091 0.8000 11 Cufflinks 0.9811 0.9811 0.9811 106 Cushion Covers 0.0000 0.0000 0.0000 1 Deodorant 0.8946 0.9539 0.9233 347 Dresses 0.7956 0.8642 0.8285 464 Duffel Bag 0.8947 0.5795 0.7034 88 Dupatta 0.9008 0.9397 0.9198 116 Earrings 0.9952 0.9880 0.9916 416 Eye Cream 1.0000 0.2500 0.4000 4 Eyeshadow 0.9062 0.9062 0.9062 32 Face Moisturisers 0.5846 0.8085 0.6786 47 Face Scrub and Exfoliator 0.0000 0.0000 0.0000 4 Face Serum and Gel 0.0000 0.0000 0.0000 2 Face Wash and Cleanser 0.6667 0.6250 0.6452 16 Flats 0.5764 0.2640 0.3621 500 Flip Flops 0.8573 0.9464 0.8996 914 Footballs 1.0000 0.3750 0.5455 8 Formal Shoes 0.8246 0.8932 0.8576 637 Foundation and Primer 0.9524 0.8696 0.9091 69 Fragrance Gift Set 0.6842 0.9123 0.7820 57 Free Gifts 0.9000 0.0989 0.1782 91 Gloves 0.9375 0.7500 0.8333 20 Hair Accessory 0.0000 0.0000 0.0000 1 Hair Colour 0.8636 1.0000 0.9268 19 Handbags 0.8840 0.9744 0.9270 1759 Hat 0.0000 0.0000 0.0000 3 Headband 1.0000 0.5714 0.7273 7 Heels 0.7622 0.9206 0.8340 1323 Highlighter and Blush 0.9697 0.8421 0.9014 38 Innerwear Vests 0.9056 0.8719 0.8884 242 Ipad 0.0000 0.0000 0.0000 1 Jackets 0.7950 0.6163 0.6943 258 Jeans 0.8118 0.9385 0.8706 602 Jeggings 1.0000 0.0882 0.1622 34 Jewellery Set 0.9333 0.9655 0.9492 58 Jumpsuit 0.0000 0.0000 0.0000 16 Kajal and Eyeliner 0.7241 0.8936 0.8000 94 Key chain 0.0000 0.0000 0.0000 2 Kurta Sets 0.8774 0.9894 0.9300 94 Kurtas 0.9348 0.9414 0.9381 1844 Kurtis 0.5000 0.5427 0.5205 234 Laptop Bag 0.6338 0.5488 0.5882 82 Leggings 0.7590 0.8362 0.7957 177 Lehenga Choli 0.0000 0.0000 0.0000 4 Lip Care 0.8000 0.5714 0.6667 7 Lip Gloss 0.8718 0.9358 0.9027 109 Lip Liner 0.8846 0.5111 0.6479 45 Lip Plumper 1.0000 0.5000 0.6667 4 Lipstick 0.9660 0.9846 0.9752 260 Lounge Pants 0.7727 0.2787 0.4096 61 Lounge Shorts 1.0000 0.1176 0.2105 34 Lounge Tshirts 0.5000 0.6667 0.5714 3 Makeup Remover 0.0000 0.0000 0.0000 2 Mascara 0.6000 0.5000 0.5455 12 Mask and Peel 0.7778 0.7000 0.7368 10 Mens Grooming Kit 0.0000 0.0000 0.0000 1 Messenger Bag 0.6818 0.3409 0.4545 44 Mobile Pouch 0.5714 0.5106 0.5393 47 Mufflers 0.8056 0.7632 0.7838 38 Nail Essentials 1.0000 0.5000 0.6667 6 Nail Polish 0.9928 0.9964 0.9946 278 Necklace and Chains 0.9375 0.9375 0.9375 160 Nehru Jackets 0.0000 0.0000 0.0000 5 Night suits 0.8792 0.9291 0.9034 141 Nightdress 0.7730 0.7606 0.7668 188 Patiala 1.0000 0.7368 0.8485 38 Pendant 0.9181 0.8920 0.9049 176 Perfume and Body Mist 0.9463 0.9055 0.9254 603 Rain Jacket 0.0000 0.0000 0.0000 7 Ring 0.8952 0.9407 0.9174 118 Robe 0.0000 0.0000 0.0000 4 Rompers 1.0000 1.0000 1.0000 12 Rucksacks 0.7143 0.4545 0.5556 11 Salwar 0.6122 0.9375 0.7407 32 Salwar and Dupatta 1.0000 0.8571 0.9231 7 Sandals 0.8618 0.8291 0.8451 895 Sarees 0.9660 0.9977 0.9816 427 Scarves 0.8333 0.7983 0.8155 119 Shapewear 0.2500 0.1111 0.1538 9 Shirts 0.9360 0.9614 0.9485 3212 Shoe Accessories 0.0000 0.0000 0.0000 3 Shoe Laces 0.0000 0.0000 0.0000 1 Shorts 0.8986 0.9232 0.9107 547 Shrug 0.0000 0.0000 0.0000 6 Skirts 0.8293 0.7969 0.8127 128 Socks 0.9869 0.9883 0.9876 686 Sports Sandals 0.6111 0.1642 0.2588 67 Sports Shoes 0.8880 0.8100 0.8472 2016 Stockings 0.8824 0.9375 0.9091 32 Stoles 0.8690 0.8111 0.8391 90 Sunglasses 0.9898 0.9991 0.9944 1073 Sunscreen 1.0000 0.7333 0.8462 15 Suspenders 1.0000 1.0000 1.0000 40 Sweaters 0.7488 0.5812 0.6545 277 Sweatshirts 0.6348 0.7930 0.7051 285 Swimwear 0.9000 0.5294 0.6667 17 Tablet Sleeve 0.0000 0.0000 0.0000 3 Ties 1.0000 0.9886 0.9943 263 Ties and Cufflinks 0.0000 0.0000 0.0000 2 Tights 1.0000 0.3333 0.5000 9 Toner 0.0000 0.0000 0.0000 2 Tops 0.7591 0.7208 0.7394 1762 Track Pants 0.8537 0.8257 0.8395 304 Tracksuits 0.8750 0.9655 0.9180 29 Travel Accessory 1.0000 0.1875 0.3158 16 Trolley Bag 0.0000 0.0000 0.0000 3 Trousers 0.9428 0.8396 0.8882 530 Trunk 0.8819 0.9071 0.8944 140 Tshirts 0.9273 0.9580 0.9424 7065 Tunics 0.6129 0.1659 0.2612 229 Umbrellas 1.0000 1.0000 1.0000 6 Waist Pouch 1.0000 0.1176 0.2105 17 Waistcoat 1.0000 0.2667 0.4211 15 Wallets 0.9491 0.9235 0.9361 928 Watches 0.9817 0.9929 0.9873 2542 Water Bottle 1.0000 0.8182 0.9000 11 Wristbands 0.8571 0.8571 0.8571 7 accuracy 0.8911 44072 macro avg 0.7131 0.6174 0.6361 44072 weighted avg 0.8877 0.8911 0.8846 44072 ``` The model predicts one of the following **article types** for fashion products, such as: - **0:** Accessory Gift Set - **1:** Baby Dolls - **2:** Backpacks - **3:** Bangle - **...** - **140:** Wristbands --- # **Run with Transformers 🤗** ```bash pip install -q transformers torch pillow gradio ``` ```python import gradio as gr from transformers import AutoImageProcessor, SiglipForImageClassification from PIL import Image import torch # Load model and processor model_name = "prithivMLmods/Fashion-Product-articleType" # Replace with your actual model path model = SiglipForImageClassification.from_pretrained(model_name) processor = AutoImageProcessor.from_pretrained(model_name) # Label mapping id2label = { 0: "Accessory Gift Set", 1: "Baby Dolls", 2: "Backpacks", 3: "Bangle", 4: "Basketballs", 5: "Bath Robe", 6: "Beauty Accessory", 7: "Belts", 8: "Blazers", 9: "Body Lotion", 10: "Body Wash and Scrub", 11: "Booties", 12: "Boxers", 13: "Bra", 14: "Bracelet", 15: "Briefs", 16: "Camisoles", 17: "Capris", 18: "Caps", 19: "Casual Shoes", 20: "Churidar", 21: "Clothing Set", 22: "Clutches", 23: "Compact", 24: "Concealer", 25: "Cufflinks", 26: "Cushion Covers", 27: "Deodorant", 28: "Dresses", 29: "Duffel Bag", 30: "Dupatta", 31: "Earrings", 32: "Eye Cream", 33: "Eyeshadow", 34: "Face Moisturisers", 35: "Face Scrub and Exfoliator", 36: "Face Serum and Gel", 37: "Face Wash and Cleanser", 38: "Flats", 39: "Flip Flops", 40: "Footballs", 41: "Formal Shoes", 42: "Foundation and Primer", 43: "Fragrance Gift Set", 44: "Free Gifts", 45: "Gloves", 46: "Hair Accessory", 47: "Hair Colour", 48: "Handbags", 49: "Hat", 50: "Headband", 51: "Heels", 52: "Highlighter and Blush", 53: "Innerwear Vests", 54: "Ipad", 55: "Jackets", 56: "Jeans", 57: "Jeggings", 58: "Jewellery Set", 59: "Jumpsuit", 60: "Kajal and Eyeliner", 61: "Key chain", 62: "Kurta Sets", 63: "Kurtas", 64: "Kurtis", 65: "Laptop Bag", 66: "Leggings", 67: "Lehenga Choli", 68: "Lip Care", 69: "Lip Gloss", 70: "Lip Liner", 71: "Lip Plumper", 72: "Lipstick", 73: "Lounge Pants", 74: "Lounge Shorts", 75: "Lounge Tshirts", 76: "Makeup Remover", 77: "Mascara", 78: "Mask and Peel", 79: "Mens Grooming Kit", 80: "Messenger Bag", 81: "Mobile Pouch", 82: "Mufflers", 83: "Nail Essentials", 84: "Nail Polish", 85: "Necklace and Chains", 86: "Nehru Jackets", 87: "Night suits", 88: "Nightdress", 89: "Patiala", 90: "Pendant", 91: "Perfume and Body Mist", 92: "Rain Jacket", 93: "Ring", 94: "Robe", 95: "Rompers", 96: "Rucksacks", 97: "Salwar", 98: "Salwar and Dupatta", 99: "Sandals", 100: "Sarees", 101: "Scarves", 102: "Shapewear", 103: "Shirts", 104: "Shoe Accessories", 105: "Shoe Laces", 106: "Shorts", 107: "Shrug", 108: "Skirts", 109: "Socks", 110: "Sports Sandals", 111: "Sports Shoes", 112: "Stockings", 113: "Stoles", 114: "Sunglasses", 115: "Sunscreen", 116: "Suspenders", 117: "Sweaters", 118: "Sweatshirts", 119: "Swimwear", 120: "Tablet Sleeve", 121: "Ties", 122: "Ties and Cufflinks", 123: "Tights", 124: "Toner", 125: "Tops", 126: "Track Pants", 127: "Tracksuits", 128: "Travel Accessory", 129: "Trolley Bag", 130: "Trousers", 131: "Trunk", 132: "Tshirts", 133: "Tunics", 134: "Umbrellas", 135: "Waist Pouch", 136: "Waistcoat", 137: "Wallets", 138: "Watches", 139: "Water Bottle", 140: "Wristbands" } def classify_article_type(image): """Predicts the article type for a fashion product.""" image = Image.fromarray(image).convert("RGB") inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): outputs = model(**inputs) logits = outputs.logits probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist() predictions = {id2label[i]: round(probs[i], 3) for i in range(len(probs))} return predictions # Gradio interface iface = gr.Interface( fn=classify_article_type, inputs=gr.Image(type="numpy"), outputs=gr.Label(label="Article Type Prediction Scores"), title="Fashion-Product-articleType", description="Upload a fashion product image to predict its article type (e.g., T-shirt, Jeans, Handbag, etc)." ) # Launch the app if __name__ == "__main__": iface.launch() ``` --- # **Intended Use** This model is best suited for: - **Fashion E-commerce Tagging & Categorization** - **Automated Product Labeling for Catalogs** - **Enhanced Product Search & Filtering** - **Retail Analytics and Product Type Breakdown**