Upload 4 files

app.py

@@ -0,0 +1,139 @@
+from flask import Flask, request, jsonify, send_file
+from tensorflow.keras.models import load_model, Model
+from PIL import Image
+import numpy as np
+import os
+import cv2
+import tensorflow as tf
+import firebase_admin
+from firebase_admin import credentials, db
+from datetime import datetime
+
+app = Flask(__name__)
+
+# ✅ 1. Initialize Firebase
+cred = credentials.Certificate("glaucoma-4b682-firebase-adminsdk-fbsvc-cd31fbe99d.json")  # Path to your service account JSON
+firebase_admin.initialize_app(cred, {
+    'databaseURL': 'https://glaucoma-4b682-default-rtdb.firebaseio.com/'
+})
+results_ref = db.reference('results')  # Will save results here
+
+# ✅ 2. Load the Model
+model = load_model('mobilenet_glaucoma_model.h5', compile=False)
+
+# ✅ 3. Preprocess Image
+def preprocess_image(img):
+    img = img.resize((224, 224))
+    img = np.array(img) / 255.0
+    img = np.expand_dims(img, axis=0)
+    return img
+
+# ✅ 4. Grad-CAM Generation
+def make_gradcam(img_array, model, last_conv_layer_name='Conv2D_1'):
+    """Generate Grad-CAM for the given image and model."""
+    last_conv_layer = model.get_layer(last_conv_layer_name)
+    grad_model = Model(inputs=model.inputs, outputs=[last_conv_layer.output, model.output])
+
+    with tf.GradientTape() as tape:
+        conv_outputs, predictions = grad_model(img_array)
+        loss = predictions[:, 0]
+    grads = tape.gradient(loss, conv_outputs)
+
+    pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
+    conv_outputs = conv_outputs[0]
+
+    for i in range(conv_outputs.shape[-1]):
+        conv_outputs[..., i] *= pooled_grads[i]
+
+    heatmap = tf.reduce_mean(conv_outputs, axis=-1).numpy()
+    heatmap = np.maximum(heatmap, 0)
+    heatmap /= np.max(heatmap)
+
+    return heatmap
+
+# ✅ 5. Save Grad-CAM Overlay
+def save_gradcam_image(original_img, heatmap, filename='gradcam.png', output_dir='results'):
+    """Save the Grad-CAM overlay image and return its path."""
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+
+    img = np.array(original_img.resize((224, 224)))
+    heatmap = cv2.resize(heatmap, (img.shape[1], img.shape[0]))
+    heatmap = np.uint8(255 * heatmap)
+
+    heatmap = cv2.applyColorMap(heatmap, cv2.COLORMAP_JET)
+    overlay = cv2.addWeighted(img, 0.6, heatmap, 0.4, 0)
+
+    filepath = os.path.join(output_dir, filename)
+    cv2.imwrite(filepath, overlay)
+
+    return filepath
+
+@app.route('/')
+def home():
+    return "Glaucoma Detection Flask API is running!"
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    """Perform prediction and save results to Firebase."""
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file uploaded'}), 400
+
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({'error': 'No file selected'}), 400
+
+    try:
+        img = Image.open(file.stream).convert('RGB')
+        img_array = preprocess_image(img)
+
+        prediction = model.predict(img_array)[0]
+        glaucoma_prob = 1 - prediction[0]
+        normal_prob = prediction[0]
+        result = 'Glaucoma' if glaucoma_prob > normal_prob else 'Normal'
+        confidence = float(glaucoma_prob) if result == 'Glaucoma' else float(normal_prob)
+
+        # Grad-CAM
+        heatmap = make_gradcam(img_array, model, last_conv_layer_name='Conv2D_1')
+        gradcam_filename = f"gradcam_{int(datetime.now().timestamp())}.png"
+        save_gradcam_image(img, heatmap, filename=gradcam_filename)
+
+        # Save to Firebase
+        results_ref.push({
+            'image_filename': file.filename,
+            'prediction': result,
+            'confidence': confidence,
+            'gradcam_filename': gradcam_filename,
+            'timestamp': datetime.now().isoformat()
+        })
+
+        return jsonify({
+            'prediction': result,
+            'confidence': confidence,
+            'normal_probability': float(normal_prob),
+            'glaucoma_probability': float(glaucoma_prob),
+            'gradcam_image': gradcam_filename
+        })
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/results', methods=['GET'])
+def results():
+    """List all results from the Firebase database."""
+    results_data = results_ref.get()
+    if not results_data:
+        results_data = []
+    return jsonify(results_data)
+
+@app.route('/gradcam/<filename>')
+def get_gradcam(filename):
+    """Serve the Grad-CAM overlay image."""
+    filepath = os.path.join('results', filename)
+    if os.path.exists(filepath):
+        return send_file(filepath, mimetype='image/png')
+    else:
+        return jsonify({'error': 'File not found'}), 404
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860)

glaucoma-4b682-firebase-adminsdk-fbsvc-cd31fbe99d.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "glaucoma-4b682",
+  "private_key_id": "cd31fbe99d9bfcd83a0f9435df4b10351a2d02d1",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\n1/78P6aIjhVuvqLmgP4wXO/q\n-----END PRIVATE KEY-----\n",
+  "client_email": "[email protected]",
+  "client_id": "107453183192663273755",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/firebase-adminsdk-fbsvc%40glaucoma-4b682.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

mobilenet_glaucoma_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678846bf6ca5c8d457c7ab2fb173c250394896bdf0d19214cb2e58ef485de9f7
+size 9587048

requirements.txt

@@ -0,0 +1,4 @@
+Flask
+tensorflow
+pillow
+numpy