Update app.py

app.py

@@ -1,65 +1,58 @@
-#import gradio as gr
-
-#def greet(name):
-#    return "Hello " + name + "!!"
-
-#demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-#demo.launch()
-
-#######################
-
-import spaces
-
-@spaces.GPU
-def main():
-    # Your existing Gradio app code here
-    import os
-    import gradio as gr
-    from transformers import AutoTokenizer, AutoModelForCausalLM
-    import torch
-
-    os.system("pip install gradio==3.50.2")
-    model_id = "codellama/CodeLlama-7b-Instruct-hf"
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    model = AutoModelForCausalLM.from_pretrained(
-        model_id, 
-        device_map="auto", 
-        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
-    )
-    tokenizer.pad_token = tokenizer.eos_token
-
-    def convert_python_to_r(python_code):
-        prompt = f"""### Task:
-Convert the following Python code to equivalent R code.
-
-### Python code:
-{python_code}
-
-### R code:"""
-        input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids
-        if torch.cuda.is_available():
-            input_ids = input_ids.to("cuda")
-
-        outputs = model.generate(
-            input_ids,
-            max_length=1024,
-            do_sample=True,
-            temperature=0.2,
-            pad_token_id=tokenizer.eos_token_id,
-            num_return_sequences=1
-        )
-        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        if "### R code:" in generated_text:
-            generated_text = generated_text.split("### R code:")[-1].strip()
-        return generated_text
-
-    gr.Interface(
-        fn=convert_python_to_r,
-        inputs=gr.Textbox(lines=10, placeholder="Paste your Python code here..."),
-        outputs="text",
-        title="Python to R Code Converter using CodeLlama 7B Instruct",
-        description="Enter Python code below, and the tool will convert it to R code using the CodeLlama 7B Instruct model."
-    ).launch()
-
-if __name__ == "__main__":
-    main()
+import gradio as gr
+from transformers import AutoModel, AutoProcessor
+import torch
+import requests
+from PIL import Image
+from io import BytesIO
+
+fashion_items = ['top', 'trousers', 'jumper']
+
+# Load model and processor
+model_name = 'Marqo/marqo-fashionSigLIP'
+model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
+processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
+
+# Preprocess and normalize text data
+with torch.no_grad():
+    # Ensure truncation and padding are activated
+    processed_texts = processor(
+        text=fashion_items,
+        return_tensors="pt",
+        truncation=True,  # Ensure text is truncated to fit model input size
+        padding=True      # Pad shorter sequences so that all are the same length
+    )['input_ids']
+    
+    text_features = model.get_text_features(processed_texts)
+    text_features = text_features / text_features.norm(dim=-1, keepdim=True)
+
+# Prediction function
+def predict_from_url(url):
+    # Check if the URL is empty
+    if not url:
+        return {"Error": "Please input a URL"}
+    
+    try:
+        image = Image.open(BytesIO(requests.get(url).content))
+    except Exception as e:
+        return {"Error": f"Failed to load image: {str(e)}"}
+    
+    processed_image = processor(images=image, return_tensors="pt")['pixel_values']
+    
+    with torch.no_grad():
+        image_features = model.get_image_features(processed_image)
+        image_features = image_features / image_features.norm(dim=-1, keepdim=True)
+        text_probs = (100 * image_features @ text_features.T).softmax(dim=-1)
+        
+    return {fashion_items[i]: float(text_probs[0, i]) for i in range(len(fashion_items))}
+
+# Gradio interface
+demo = gr.Interface(
+    fn=predict_from_url, 
+    inputs=gr.Textbox(label="Enter Image URL"),
+    outputs=gr.Label(label="Classification Results"), 
+    title="Fashion Item Classifier",
+    allow_flagging="never"
+)
+
+# Launch the interface
+demo.launch()