app.py

import gradio as gr
from transformers import ImageClassificationPipeline, PerceiverForImageClassificationConvProcessing, PerceiverFeatureExtractor
import torch

torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
 
feature_extractor = PerceiverFeatureExtractor()
model = PerceiverForImageClassificationConvProcessing.from_pretrained("deepmind/vision-perceiver-conv")

# define custom pipeline as Perceiver expects "inputs" rather than "pixel_values"
class CustomPipeline(ImageClassificationPipeline):
    def _forward(self, model_inputs):
        inputs = model_inputs["pixel_values"]
        model_outputs = self.model(inputs=inputs)
        return model_outputs

image_pipe = CustomPipeline(model=model, feature_extractor=feature_extractor)

def classify_image(image):
  results = image_pipe(image)
  # convert to format Gradio expects
  output = {}
  for prediction in results:
    predicted_label = prediction['label']
    score = prediction['score']
    output[predicted_label] = score
  return output

image = gr.inputs.Image(type="pil")
label = gr.outputs.Label(num_top_classes=5)
examples = [["cats.jpg"]]

gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples, enable_queue=True).launch(debug=True)