Create app.py

app.py

@@ -0,0 +1,59 @@
+import numpy as np
+import tensorflow as tf
+import gradio as gr
+from huggingface_hub import from_pretrained_keras
+
+model = from_pretrained_keras("keras-io/conv_mixer_image_classification")
+
+class_names = [
+    "Airplane",
+    "Automobile",
+    "Bird",
+    "Cat",
+    "Deer",
+    "Dog",
+    "Frog",
+    "Horse",
+    "Ship",
+    "Truck",
+]
+
+examples = [
+    ['./aeroplane.png'],
+    ['./horse.png'],
+    ['./ship.png'],
+    ['./truck.png']
+] 
+
+IMG_SIZE = 32
+
+def infer(input_image):
+    image_tensor = tf.convert_to_tensor(input_image)
+    image_tensor.set_shape([None, None, 3])
+    image_tensor = tf.image.resize(image_tensor, (IMG_SIZE, IMG_SIZE))
+    predictions = model.predict(np.expand_dims((image_tensor), axis=0))
+    predictions = np.squeeze(predictions)
+    predictions = np.argmax(predictions)
+    predicted_label = class_names[predictions.item()]
+    return str(predicted_label)
+
+    
+input = gr.inputs.Image(shape=(IMG_SIZE, IMG_SIZE))
+output = [gr.outputs.Label(label = "Output")]
+
+title = "Image Classification using Conv Mixer Model"
+description = "Upload an image or select from examples to classify it.<br>The allowed classes are - Airplane, Automobile, Bird, Cat, Deer, Dog, Frog, Horse, Ship, Truck.<br><p><b>Model Repo - https://huggingface.co/keras-io/conv_mixer_image_classification</b> <br><b>Keras Example - https://keras.io/examples/vision/convmixer//</b></p>"
+
+
+article = "<div style='text-align: center;'><a href='https://twitter.com/_Blazer_007' target='_blank'>Space by Vivek Rai</a><br><a href='https://twitter.com/RisingSayak' target='_blank'>Keras example by Sayak Paul</a></div>"
+
+gr_interface = gr.Interface(
+    infer, 
+    input, 
+    output, 
+    examples=examples, 
+    allow_flagging=False, 
+    analytics_enabled=False, 
+    title=title, 
+    description=description,
+    article=article).launch(enable_queue=True, debug=True)