Add initial implementation of Fashion Item Detector with Gradio interface

README.md

@@ -11,4 +11,6 @@ license: unknown
 short_description: upload image and get outfit price tags
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Fashion Item Detector
+Upload an image to detect clothing, accessories, and details using the YOLOS-Fashionpedia model.
+Built with Gradio and Transformers.

app.py

@@ -0,0 +1,68 @@
+import gradio as gr
+from transformers import AutoImageProcessor, AutoModelForObjectDetection
+from PIL import Image, ImageDraw, ImageFont
+import torch 
+
+# Load the model and processor
+model_name = "valentinafeve/yolos-fashionpedia"
+processor = AutoImageProcessor.from_pretrained(model_name)
+model = AutoModelForObjectDetection.from_pretrained(model_name)
+
+# Define the 46 fashion categories (id2label mapping)
+CATS = [
+    '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'
+]
+model.config.id2label = {i: label for i, label in enumerate(CATS)}
+model.config.label2id = {label: i for i, label in model.config.id2label.items()}
+
+def detect_fashion_items(image):
+    # Prepare inputs
+    inputs = processor(images=image, return_tensors="pt")
+    
+    # Move to GPU if available
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+    
+    # Run inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Post-process
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = processor.post_process_object_detection(
+        outputs, threshold=0.5, target_sizes=target_sizes
+    )[0]
+    
+    # Draw on the image
+    draw = ImageDraw.Draw(image)
+    try:
+        font = ImageFont.truetype("DejaVuSans.ttf", 200)  # Colab-compatible font
+    except:
+        font = ImageFont.load_default()  # Fallback if font fails
+    
+    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+        box = [round(i, 2) for i in box.tolist()]
+        # Draw bounding box (blue rectangle)
+        draw.rectangle(box, outline="blue", width=3)
+        # Draw label with confidence
+        label_text = f"{model.config.id2label[label.item()]}: {score:.2f}"
+        draw.text((box[0], box[1] - 20), label_text, fill="blue", font=font)
+    
+    return image
+
+# Gradio interface
+iface = gr.Interface(
+    fn=detect_fashion_items,
+    inputs=gr.Image(type="pil", label="Upload a fashion image"),
+    outputs=gr.Image(type="pil", label="Detected fashion items"),
+    title="Fashion Item Detector",
+    description="Upload an image to detect clothing, accessories, and details using YOLOS-Fashionpedia."
+)
+ 
+# Launch Gradio (Colab-compatible)
+iface.launch(share=True)  # Creates a public URL

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+gradio
+pillow