Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import numpy as np
+import tensorflow as tf
+from PIL import Image
+
+# Load the TensorFlow Lite model
+interpreter = tf.lite.Interpreter(model_path="pneumonia_classifier.tflite")
+interpreter.allocate_tensors()
+
+# Get input and output tensors
+input_details = interpreter.get_input_details()
+output_details = interpreter.get_output_details()
+
+# Define a function to resize the input image
+def resize_image(image):
+    image_resized = tf.image.resize(image, [224, 224])
+    return image_resized.numpy()
+
+# Define a function to perform inference on the TensorFlow Lite model
+def classify_image(image):
+    image_resized = resize_image(image)
+    input_data = np.expand_dims(image_resized, axis=0).astype(np.float32)
+    interpreter.set_tensor(input_details[0]['index'], input_data)
+    interpreter.invoke()
+    output_data = interpreter.get_tensor(output_details[0]['index'])
+    return output_data[0]
+
+# Define the labels for pneumonia classes
+labels = ['0: Normal', '1: Pneumonia']
+
+# Define the main Gradio app
+def pneumonia_classification(image):
+    pil_image = Image.fromarray(image.astype('uint8'), 'RGB')
+    probabilities = classify_image(pil_image)
+    prediction = labels[np.argmax(probabilities)]
+    return {
+        "Prediction": prediction,
+        "Probability": f"{probabilities.max() * 100:.2f}%"
+    }
+
+# Create the Gradio interface
+gr.Interface(
+    fn=pneumonia_classification,
+    inputs="image",
+    outputs="json",
+    title="Pneumonia Classification",
+    examples=["normal.jpg", "pneumonia.jpg"],
+    description="""The app provides users with the ability to classify chest X-ray images as 'Normal' or 'Pneumonia'. Please upload an image of a chest X-ray to classify it and provide information about the prediction.""",
+).launch()