create app.py

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+from PIL import Image
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2,preprocess_input, decode_predictions
+
+model = MobileNetV2(weights='imagenet')
+
+def preprocess_image(image):
+    img = image.resize((224,224))
+    img_array = np.array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = preprocess_input(img_array)
+    return img_array
+
+def predict(image):
+    img_array = preprocess_image(image)
+    preds = model.predict(img_array)
+    decoded_preds = decode_predictions(preds, top=1)[0]
+    return decoded_preds
+
+def main():
+    st.set_page_config(page_title='Image Classification', page_icon=":camera_flash:")
+    st.title('Image Classification with MobileNetV2')
+    st.sidebar.title("Options")
+
+    st.sidebar.write('Upload an image for classification')
+
+    uploaded_file = st.sidebar.file_uploader("", type=["jpg", "jpeg", "png"])
+
+    if uploaded_file is not None:
+
+        image = Image.open(uploaded_file)
+        st.image(image, caption='Uploaded Image', use_column_width=True)
+
+        if st.button('Classify'):
+            with st.spinner('Classifying...'):
+                prediction = predict(image)
+            st.success('Classification done!')
+
+            st.write('*Prediction:*')
+            imagenet_id, label, score = prediction[0]
+            st.write(f"- *{label}* (Confidence: {score:2%})")
+
+if _name_ == '_main_':
+    main()