new comments

app.py

@@ -5,8 +5,10 @@ import matplotlib.pyplot as plt
 import numpy as np
 import PIL.Image
 
+# Load model from TF-Hub
 hub_model = hub.load('https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2') 
 
+# Function to convert tensor to image
 def tensor_to_image(tensor):
     tensor = tensor*255
     tensor = np.array(tensor, dtype=np.uint8)
@@ -15,20 +17,27 @@ def tensor_to_image(tensor):
       tensor = tensor[0]
     return PIL.Image.fromarray(tensor)
 
+# Stylize function
 def stylize(content_image, style_image):
+    # Convert to float32 numpy array, add batch dimension, and normalize to range [0, 1]. Example using numpy:
     content_image = content_image.astype(np.float32)[np.newaxis, ...] / 255.
     style_image = style_image.astype(np.float32)[np.newaxis, ...] / 255.
+    # Stylize image
     stylized_image = hub_model(tf.constant(content_image), tf.constant(style_image))[0]
     return tensor_to_image(stylized_image)
-    
+
+# Add image examples for users    
 paris =[["example_paris.jpeg"], ["example_vangogh.jpeg"]]
 aristotle = [["example_aristotle.jpeg"], ["example_dali.jpeg"]]
 avatar = [["example_avatar.jpeg"], ["example_kandinsky.jpeg"]]
+
+# Customize interface
 title = "Fast Neural Style Transfer using TF-Hub"
-description = "Demo for neural style transfer using the pretrained Arbitrary Image Stylization model from TensorFlow Hub."
+description = "\nDemo for neural style transfer using the pretrained Arbitrary Image Stylization model from TensorFlow Hub.\n"
 content_input = gr.inputs.Image(label="Content Image", source="upload")
 style_input = gr.inputs.Image(label="Style Image", source="upload")
 
+# Build and launch
 iface = gr.Interface(fn=stylize, 
                      inputs=[content_input, style_input], 
                      outputs="image",