Add application file

app.py

@@ -0,0 +1,74 @@
+import os
+import gradio as gr
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+import numpy as np
+
+# Load the pre-trained model
+try:
+    model = load_model("my_model.h5")
+except OSError as e:
+    print(f"Error loading model: {e}")
+
+
+def classify_image(image):
+    try:
+        # Preprocess the image
+        image_gray = tf.image.rgb_to_grayscale(image)
+
+        # Resize the image to 32x32 (only once)
+        image_tensor = tf.image.resize(image_gray, (32, 32))
+
+        # Cast to float32
+        image_tensor = tf.cast(image_tensor, tf.float32)
+
+        # Add batch dimension
+        image_tensor = tf.expand_dims(image_tensor, 0)
+
+        # Normalize the data
+        image_tensor = image_tensor / 255.0
+
+        # Get the prediction
+        predictions = model.predict(image_tensor)
+
+        # For top-3 output format compatible with Gradio
+        if predictions.shape[1] == 10:  # For MNIST (0-9 digits)
+            class_names = {i: str(i) for i in range(10)}
+            top_indices = np.argsort(predictions[0])[-3:][::-1]  # Top 3 indices
+            confidences = {
+                class_names[i]: float(predictions[0][i]) for i in top_indices
+            }
+            return confidences
+        else:
+            # Fallback to simple argmax if model output doesn't match expected format
+            return {str(predictions.argmax()): float(predictions.max())}
+
+    except Exception as e:
+        return {"Error": str(e)}
+
+
+# Check if examples directory exists
+example_list = []
+if os.path.exists("examples"):
+    example_list = [
+        ["examples/" + example]
+        for example in os.listdir("examples")
+        if os.path.isfile(os.path.join("examples", example))
+    ]
+
+title = "MNIST Model 98% Accuracy"
+description = "Model trained on MNIST dataset using EfficientNet to classify handwritten digits with 98% accuracy"
+article = "For source code, visit [my GitHub](https://github.com/Bijan-K/Tensorflow-MNIST-98Acc.git) (includes Gradio implementation and training code)."
+
+interface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Label(num_top_classes=3),
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article,
+)
+
+if __name__ == "__main__":
+    interface.launch()

my_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1b5ca4fe6a8a40dc1e92b132417c44b2d84b472a99ebfdfecd4b6da9e936a3
+size 49261456

requirements.txt

@@ -0,0 +1,5 @@
+tensorflow>=2.6.0
+efficientnet>=1.1.0
+gradio>=2.8.0
+pillow>=8.0.0
+numpy>=1.19.5