from transformers import AutoFeatureExtractor, RegNetForImageClassification
import torch
import gradio as gr

feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/regnet-y-040")
model = RegNetForImageClassification.from_pretrained("facebook/regnet-y-040")

def inference(image):
  print("Type of image", type(image))
  inputs = feature_extractor(image, return_tensors="pt")

  with torch.no_grad():
      logits = model(**inputs).logits

  predicted_label = logits.argmax(-1).item()
  return model.config.id2label[predicted_label]
  
title="RegNet-image-classification"
description="This space uses RegNet Model with an image classification head on top (a linear layer on top of the pooled features). It predicts one of the 1000 ImageNet classes. Check [Docs](https://huggingface.co/docs/transformers/main/en/model_doc/regnet) for more details."

examples=[['wolf.jpg'], ['ballon.jpg'], ['fountain.jpg']]
iface = gr.Interface(inference, inputs=gr.inputs.Image(), outputs="text",title=title,description=description,examples=examples)
iface.launch(enable_queue=True)