Create app.py

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+from transformers import DetrImageProcessor, DetrForObjectDetection, pipeline
+from PIL import Image
+
+# Load pre-trained image recognition model
+detection_model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
+detection_processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
+
+# Load text generation model
+description_generator = pipeline("text-generation", model="gpt-2")
+
+# Function for recognizing product
+def recognize_and_describe(image):
+    # Recognize product
+    inputs = detection_processor(images=image, return_tensors="pt")
+    outputs = detection_model(**inputs)
+    logits = outputs.logits.argmax(-1).item()
+    product_label = f"Product Class: {logits}"  # Replace with class-to-label mapping if needed
+
+    # Generate description
+    prompt = f"Describe the product: {product_label}"
+    description = description_generator(prompt, max_length=50, num_return_sequences=1)
+    return product_label, description[0]["generated_text"]
+
+# Create Gradio Interface
+interface = gr.Interface(
+    fn=recognize_and_describe,
+    inputs="image",
+    outputs=["text", "text"],
+    title="SETA: Product Description App",
+    description="Upload a product image to get its description."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    interface.launch()