more edits

app.py

@@ -16,14 +16,10 @@ model = ViTForImageClassification(config)
 #print(config)
 
 feature_extractor = ViTFeatureExtractor()
-
 # or, to load one that corresponds to a checkpoint on the hub:
 #feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
 
-
-image = "cats.jpg"
-
- 
+#the following gets called by classify_image() 
 feature_extractor = PerceiverFeatureExtractor.from_pretrained("deepmind/vision-perceiver-conv")
 model = PerceiverForImageClassificationConvProcessing.from_pretrained("deepmind/vision-perceiver-conv")
 
@@ -39,12 +35,14 @@ def classify_image(image):
     output[predicted_label] = score
   return output
 
+
 image = gr.inputs.Image(type="pil")
+image_piped = image_pipe(image)
 label = gr.outputs.Label(num_top_classes=5)
 examples = [["cats.jpg"], ["dog.jpg"]]
-title = "Interactive demo: Perceiver for image classification"
-description = "Demo for classifying images with Perceiver IO. To use it, simply upload an image or use the example images below and click 'submit' to let the model predict the 5 most probable ImageNet classes. Results will show up in a few seconds."
-article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2107.14795'>Perceiver IO: A General Architecture for Structured Inputs & Outputs</a> | <a href='https://deepmind.com/blog/article/building-architectures-that-can-handle-the-worlds-data/'>Official blog</a></p>"
+title = "Generate a Story from an Image"
+description = "Demo for classifying images with Perceiver IO. To use it, simply upload an image and click 'submit' to let the model predict the 5 most probable ImageNet classes. Results will show up in a few seconds."  + image_piped
+article = "<p style='text-align: center'></p>"
 
 gr.Interface(fn=classify_image, inputs=image, outputs=label, title=title, description=description, examples="", enable_queue=True).launch(debug=True)