Update app.py

app.py

@@ -4,24 +4,32 @@ from tensorflow.keras.models import load_model
 import numpy as np
 from tensorflow.keras.preprocessing import image
 
+my_model = load_model('Brain_Tumor_Model.h5')
 
+# Set a threshold for binary classification
+threshold = 0.5
 
 def predict_input_image(img):
     # Normalize the image by cropping (center crop)
-    h, w = img.shape[:2]
+    # Normalize the image by cropping (center crop)
+    h, w = img.size
     crop_start_x = (w - 224) // 2
     crop_start_y = (h - 224) // 2
-    img = img[crop_start_y:crop_start_y+224, crop_start_x:crop_start_x+224]
-    img = tf.image.resize(img, [224,224])
-    img = np.expand_dims(img, axis = 0)
-    
-    # Make predictions
-    model = tf.keras.models.load_model('Tumor_Model.h5')
-    prediction = model.predict(img)
-    result = 'No Tumor Detected' if prediction[0][0] > 0.5 else 'Tumor detected'
-    
+    img = img.crop((crop_start_x, crop_start_y, crop_start_x + 224, crop_start_y + 224))
+    img = img.resize((224, 224))
+
+    # Convert the image to a format suitable for model prediction
+    #img_array = np.array(img) / 255.0  # Normalize pixel values to [0, 1]
+    img_array = np.expand_dims(img, axis=0)
+
+    # Make predictions using your model
+    predictions = my_model.predict(img_array)
+
+    # Convert predictions to binary (0 or 1) based on the threshold
+    binary_prediction = 'Tumor Detected' if predictions[0][0] > threshold else 'No Tumor Detected'
 
-    return prediction
+    # Print or use the binary prediction as needed
+    print("Prediction:", binary_prediction)