Create app.py

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+# Load the trained model
+model = tf.keras.models.load_model('my_model (3).keras')
+
+# Get class names from the training data generator (assuming 'train' is still in scope from previous execution)
+# If 'train' is not in scope, you would need to define class_indices manually or reload data generators.
+# For this example, let's assume 'train.class_indices' is available or define a placeholder.
+
+# If `train` is not available, uncomment and modify the line below based on your actual classes:
+idx_to_class = {0: 'glioma', 1: 'meningioma', 2: 'notumor', 3: 'pituitary'}
+
+# Using the `idx_to_class` from previous execution
+# If `idx_to_class` is not defined, please refer to the notebook output from the prediction cell.
+class_labels = list(idx_to_class.values())
+
+# Define the image size used for training
+img_size = 224
+
+def predict_image(image):
+    # Preprocess the image
+    img = Image.fromarray(image)
+    img = img.resize((img_size, img_size))
+    img_array = np.array(img)
+    img_array = np.expand_dims(img_array, axis=0) # Add batch dimension
+
+    # Apply the same preprocessing function as during training
+    # (EfficientNet's preprocess_input function was used)
+    img_array = tf.keras.applications.efficientnet.preprocess_input(img_array)
+
+    # Make prediction
+    predictions = model.predict(img_array)[0]
+
+    # Get predicted class and confidence
+    predicted_class_idx = np.argmax(predictions)
+    predicted_class_label = class_labels[predicted_class_idx]
+    confidence = predictions[predicted_class_idx] * 100
+
+    return predicted_class_label, f"{confidence:.2f}%"
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=gr.Image(type="numpy", label="Upload MRI Scan"),
+    outputs=[
+        gr.Textbox(label="Predicted Class"),
+        gr.Textbox(label="Confidence")
+    ],
+    title="Brain Tumor MRI Classification",
+    description="Upload an MRI scan to get a prediction for brain tumor type and confidence.",
+)
+
+# Launch the interface
+iface.launch(debug=True)