Create app.py

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from transformers import ImageClassificationPipeline, PerceiverForImageClassificationConvProcessing, PerceiverFeatureExtractor
+ 
+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)
+
+gr.Interface(fn=classify_image, inputs=image, outputs=label, enable_queue=True).launch(debug=True)