Update app.py

app.py

@@ -13,7 +13,11 @@ st.markdown('The predicting result will be "Palm", or "Others".')
 st.markdown('You can click "Browse files" multiple times until adding all images before generating prediction.\n')
 
 uploaded_file = st.file_uploader("Upload an image file", type="jpg", accept_multiple_files=True)
-st.image(uploaded_file, width=100)
+
+imageContainer = st.empty()
+imageContainer.image(uploaded_file, width=100)
+
+closeImage = st.button("clear all images")
 
 img_height = 224
 img_width = 224
@@ -21,15 +25,21 @@ class_names = ['Palm', 'Others']
 
 model = tf.keras.models.load_model('model')
 
-if uploaded_file is not None:
-    Generate_pred = st.button("Generate Prediction")
-    if Generate_pred:
-        for file in uploaded_file:
-            img = Image.open(file)
-            img_array = img_to_array(img)
-            img_array = tf.expand_dims(img_array, axis = 0) # Create a batch
-            processed_image = preprocess_input(img_array)
+while(1):
+    if uploaded_file is not None:
+        Generate_pred = st.button("Generate Prediction")
+        if Generate_pred:
+            for file in uploaded_file:
+                img = Image.open(file)
+                img_array = img_to_array(img)
+                img_array = tf.expand_dims(img_array, axis = 0) # Create a batch
+                processed_image = preprocess_input(img_array)
+        
+                predictions = model.predict(processed_image)
+                score = predictions[0]
+                st.markdown("Predicted class of the image {} is : {}".format(file, class_names[np.argmax(score)]))
     
-            predictions = model.predict(processed_image)
-            score = predictions[0]
-            st.markdown("Predicted class of the image {} is : {}".format(file, class_names[np.argmax(score)]))
+    if closeImage:
+        imageContainer.empty()
+        if uploaded_file is not None:
+            del uploaded_file