initial backend

app.py

@@ -0,0 +1,74 @@
+from flask import Flask, request, jsonify
+import tensorflow as tf
+from flask_cors import CORS
+from utils import predict_image
+import os
+import requests
+
+app = Flask(__name__)
+CORS(app)
+
+# ------------------------------
+# MODEL CONFIG
+# ------------------------------
+
+MODEL_PATH = "model.h5"
+MODEL_URL = "https://huggingface.co/bakhili/stroke-classification-resnet-model/resolve/main/stroke_classification_model.h5"
+
+# ------------------------------
+# DOWNLOAD MODEL IF NOT EXISTS
+# ------------------------------
+
+if not os.path.exists(MODEL_PATH):
+    print("Downloading model from Hugging Face...")
+    r = requests.get(MODEL_URL, stream=True)
+
+    with open(MODEL_PATH, "wb") as f:
+        for chunk in r.iter_content(chunk_size=8192):
+            if chunk:
+                f.write(chunk)
+
+    print("Model downloaded successfully!")
+
+# ------------------------------
+# LOAD MODEL
+# ------------------------------
+
+print("Loading model...")
+model = tf.keras.models.load_model(MODEL_PATH)
+print("Model loaded successfully!")
+
+# ------------------------------
+# ROUTES
+# ------------------------------
+
+@app.route("/")
+def home():
+    return "Stroke Detection Backend Running"
+
+@app.route("/predict", methods=["POST"])
+def predict():
+    try:
+        if "file" not in request.files:
+            return jsonify({"error": "No file uploaded"}), 400
+
+        file = request.files["file"]
+
+        if file.filename == "":
+            return jsonify({"error": "Empty filename"}), 400
+
+        result = predict_image(model, file)
+
+        return jsonify(result)
+
+    except Exception as e:
+        print("Error during prediction:", str(e))
+        return jsonify({"error": "Prediction failed"}), 500
+
+
+# ------------------------------
+# RUN SERVER
+# ------------------------------
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,7 @@
+flask
+flask-cors
+tensorflow
+numpy
+pillow
+gunicorn
+requests

runtime.txt

@@ -0,0 +1 @@
+python-3.10

utils.py

@@ -0,0 +1,35 @@
+# Utility functions can go here
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+CLASS_NAMES = ['hemorrhagic_stroke', 'ischemic_stroke', 'no_stroke']
+
+def preprocess_image(image_file, target_size=(224, 224)):
+    """
+    Preprocess uploaded image for prediction
+    """
+    img = Image.open(image_file).convert("RGB")
+    img = img.resize(target_size)
+
+    img_array = tf.keras.utils.img_to_array(img)
+    img_array = tf.expand_dims(img_array, 0)
+
+    return img_array
+
+
+def predict_image(model, image_file):
+    """
+    Predict stroke type
+    """
+    processed = preprocess_image(image_file)
+
+    predictions = model.predict(processed)
+    index = np.argmax(predictions[0])
+
+    confidence = float(np.max(predictions[0]) * 100)
+
+    return {
+        "prediction": CLASS_NAMES[index],
+        "confidence": round(confidence, 2)
+    }