Upload 2 files

app.py.py

@@ -0,0 +1,80 @@
+import streamlit as st
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+from transformers import AutoModelForImageClassification, AutoProcessor
+from PIL import Image
+import io
+import fitz
+import torch
+
+app = Flask(__name__)
+CORS(app)
+
+model_name = "AsmaaElnagger/Diabetic_RetinoPathy_detection"
+model = AutoModelForImageClassification.from_pretrained(model_name)
+processor = AutoProcessor.from_pretrained(model_name)
+
+def pdf_to_images_pymupdf(pdf_data):
+    try:
+        pdf_document = fitz.open(stream=pdf_data, filetype="pdf")
+        images = []
+        for page_num in range(pdf_document.page_count):
+            page = pdf_document.load_page(page_num)
+            pix = page.get_pixmap()
+            img_data = pix.tobytes("jpeg")
+            images.append(img_data)
+        return images
+    except Exception as e:
+        print(f"Error converting PDF: {e}")
+        return None
+
+@app.route('/classify', methods=['POST', 'OPTIONS'])
+def classify_file():
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file provided'}), 400
+
+    uploaded_file = request.files['file']
+    file_type = uploaded_file.filename.rsplit('.', 1)[1].lower()
+
+    try:
+        if file_type in ['jpg', 'jpeg', 'png', 'gif']:
+            img_data = uploaded_file.read()
+            image = Image.open(io.BytesIO(img_data)).convert("RGB")
+            inputs = processor(images=image, return_tensors="pt")
+            with torch.no_grad():
+                outputs = model(**inputs)
+            logits = outputs.logits
+            predicted_class_idx = logits.argmax(-1).item()
+            result = model.config.id2label[predicted_class_idx]
+            return jsonify({'result': result})
+
+        elif file_type == 'pdf':
+            pdf_data = uploaded_file.read()
+            images = pdf_to_images_pymupdf(pdf_data)
+
+            if images:
+                image = Image.open(io.BytesIO(images[0])).convert("RGB")
+                inputs = processor(images=image, return_tensors="pt")
+                with torch.no_grad():
+                    outputs = model(**inputs)
+                logits = outputs.logits
+                predicted_class_idx = logits.argmax(-1).item()
+                result = model.config.id2label[predicted_class_idx]
+                return jsonify({'result': result})
+            else:
+                return jsonify({'error': 'PDF conversion failed.'}), 500
+
+        else:
+            return jsonify({'error': 'Unsupported file type'}), 400
+
+    except Exception as e:
+        return jsonify({'error': f'An error occurred: {e}'}), 500
+
+def main():
+    st.title("RetinApp Backend Status")
+    st.write("Flask backend is running and ready for classification requests.")
+
+if __name__ == '__main__':
+    main() # Run the Streamlit app (which will also run the Flask app)
+    # The Flask app will be accessible on the same server where Streamlit is running.
+    # When deployed on Hugging Face Spaces, Streamlit will handle the serving.

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+flask
+flask-cors
+transformers
+torch
+Pillow
+PyMuPDF