Upload 2 files

fashionclip_segmented_app.py

@@ -0,0 +1,66 @@
+# fashionclip_segmented_app.py
+import gradio as gr
+from PIL import Image
+import torch
+import numpy as np
+from rembg import remove
+from transformers import CLIPProcessor, CLIPModel
+
+# Lade das Modell und den Prozessor
+model = CLIPModel.from_pretrained("patrickjohncyh/fashion-clip")
+processor = CLIPProcessor.from_pretrained("patrickjohncyh/fashion-clip")
+
+# Prompts für jede Merkmalsgruppe
+category_prompts = ["a t-shirt", "a long-sleeved shirt", "a hoodie", "a sweatshirt", "a pullover", "a tank top"]
+color_prompts = ["a red garment", "a blue garment", "a black garment", "a white garment", "a green garment", "a yellow garment", "a gray garment", "a brown garment", "a pink garment", "a purple garment"]
+pattern_prompts = ["a plain shirt", "a striped shirt", "a floral shirt", "a checked shirt", "a dotted shirt", "an abstract patterned shirt"]
+fit_prompts = ["a slim fit shirt", "an oversized top", "a regular fit shirt", "a cropped shirt", "a shirt with a crew neck", "a shirt with a v-neck", "a shirt with a round neckline"]
+
+# Funktion zur Hintergrundentfernung
+def remove_background(image: Image.Image) -> Image.Image:
+    image_np = np.array(image)
+    image_no_bg_np = remove(image_np)
+    return Image.fromarray(image_no_bg_np)
+
+# Hilfsfunktion: finde das passendste Prompt für eine Gruppe
+def predict_best_prompt(image, prompts):
+    print(f"[DEBUG] Image type: {type(image)}, Prompt count: {len(prompts)}")
+    image_clean = remove_background(image)
+    inputs = processor(text=prompts, images=[image_clean], return_tensors="pt", padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits_per_image = outputs.logits_per_image
+        probs = logits_per_image.softmax(dim=1).squeeze().tolist()
+    best_idx = torch.tensor(probs).argmax().item()
+    return prompts[best_idx], probs[best_idx]
+
+# Hauptfunktion für die App
+def analyze_image(image):
+    if image is None:
+        return "⚠️ Please upload or take a picture first."
+
+    results = {}
+    results["Category"], cat_score = predict_best_prompt(image, category_prompts)
+    results["Color"], color_score = predict_best_prompt(image, color_prompts)
+    results["Pattern"], pattern_score = predict_best_prompt(image, pattern_prompts)
+    results["Fit"], fit_score = predict_best_prompt(image, fit_prompts)
+
+    return f"""
+    Category: {results['Category']} ({cat_score:.2f})\n
+    Color: {results['Color']} ({color_score:.2f})\n
+    Pattern: {results['Pattern']} ({pattern_score:.2f})\n
+    Fit: {results['Fit']} ({fit_score:.2f})
+    """
+
+# Gradio UI erstellen
+iface = gr.Interface(
+    fn=analyze_image,
+    inputs=gr.Image(type="pil", label="Upload or take a picture", sources=["upload", "webcam"]),
+    outputs="text",
+    title="Fashion Attribute Predictor (Prototype 2 + Segmentation)",
+    description="Upload or capture an image of a t-shirt or pullover. The model first removes the background and then predicts category, color, pattern, and fit using FashionCLIP."
+)
+
+# App starten
+if __name__ == "__main__":
+    iface.launch()

requirements_segmented.txt

@@ -0,0 +1,6 @@
+gradio
+torch
+transformers
+rembg
+Pillow
+numpy