Update app.py

app.py

@@ -1,11 +1,40 @@
+import cv2
 import gradio as gr
+import tensorflow as tf
+import numpy as np
 
+# Load the trained model
+model = tf.keras.models.load_model("number_recognition_model_colab.keras")
 
-def greet(name):
-    return "Hello " + name + "!"
+# Image size and labels
+img_size = 28
+labels = ["zero", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine"]
 
+# Prediction function
+def predict(img):
+    try:
+        # Ensure the image is a NumPy array and grayscale
+        img = cv2.cvtColor(np.array(img), cv2.COLOR_BGR2GRAY)
+        img = cv2.resize(img, (img_size, img_size))
+        img = img.astype("float32") / 255.0
+        img = img.reshape(1, img_size, img_size, 1)
 
-demo = gr.Interface(fn=greet, inputs="textbox", outputs="textbox")
+        # Make predictions
+        preds = model.predict(img)[0]
+        return {label: float(pred) for label, pred in zip(labels, preds)}
+    except Exception as e:
+        return {"Error": str(e)}
 
+# Gradio interface
 if __name__ == "__main__":
+    demo = gr.Interface(
+        fn=predict,  # Function to call
+        inputs=gr.Sketchpad(label="Draw a number"),  # Sketchpad input
+        outputs=gr.Label(num_top_classes=3),  # Label output to show top 3 predictions
+        title="Number Recognition App",
+        description=(
+            "The model was trained to classify numbers (from 0 to 9). "
+            "Draw a number in the sketchpad below and see the prediction!"
+        )
+    )
     demo.launch()