Create app.py

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+# Load your pre-trained model
+def load_model():
+    model = tf.keras.models.load_model('depi-graduation-project (1).ipynb')  # Replace with your model's path
+    return model
+
+model = load_model()
+
+# Define the labels (categories)
+labels = ['Water', 'Cloudy', 'Desert', 'Green Area']
+
+# Function to preprocess the image and predict the class
+def classify_image(image):
+    img = image.resize((128, 128))  # Resize the image
+    img = np.array(img) / 255.0     # Normalize the image
+    img = np.expand_dims(img, axis=0)  # Add batch dimension
+    prediction = model.predict(img)
+    predicted_class = labels[np.argmax(prediction)]
+    
+    # Prepare output with probabilities
+    return {labels[i]: float(prediction[0][i]) for i in range(len(labels))}
+
+# Define the Gradio interface
+image_input = gr.inputs.Image(shape=(128, 128))
+label_output = gr.outputs.Label(num_top_classes=4)
+
+# Launch the interface
+gr.Interface(fn=classify_image, 
+             inputs=image_input, 
+             outputs=label_output, 
+             title="Satellite Image Classification", 
+             description="Classify satellite images into four types: Water, Cloudy, Desert, Green Area").launch()