format

app.py

@@ -21,6 +21,7 @@ classif_pipeline = pipeline(
     "image-classification", model=classif_model, feature_extractor=feature_extractor
 )
 
+
 def load_manifest(inputs):
     with requests.get(inputs) as r:
         return r.json()
@@ -39,11 +40,10 @@ def resize_iiif_urls(image_url, size='224'):
     # parts[6] = f"{size}, {size}"
     # return "/".join(parts)
     image_url = IIIFImageClient.init_from_url(image_url)
-    image_url = image_url.size(width=size,height=size)
+    image_url = image_url.size(width=size, height=size)
     return image_url.__str__()
 
 
-
 async def get_image(client, url):
     try:
         resp = await client.get(url, timeout=30)
@@ -62,6 +62,11 @@ async def get_images(urls):
 
 
 def predict(inputs):
+    return _predict(str(inputs))
+
+
+@lru_cache()
+def _predict(inputs):
     data = load_manifest(inputs)
     urls = get_image_urls_from_manifest(data)
     resized_urls = [resize_iiif_urls(url) for url in urls]
@@ -70,7 +75,7 @@ def predict(inputs):
     images = list(pluck(1, images_urls))
     urls = list(pluck(0, images_urls))
     predictions = classif_pipeline(images, top_k=1)
-    for url, pred in zip(urls,predictions):
+    for url, pred in zip(urls, predictions):
         top_pred = pred[0]
         if top_pred['label'] == 'illustrated':
             image_url = IIIFImageClient.init_from_url(url)
@@ -86,6 +91,7 @@ def predict(inputs):
     #         predicted_images.append((image, top_pred['score']))
     #     return predicted_images
 
+
 gallery = gr.Gallery()
 gallery.style(grid=3)
 
@@ -95,5 +101,6 @@ demo = gr.Interface(
     outputs=gallery,
     title="ImageIN",
     description="Identify illustrations in pages of historical books!",
+    examples=['https://iiif.lib.harvard.edu/manifests/drs:427603172']
 )
 demo.launch(debug=True)