from transformers import ViTImageProcessor, ViTForImageClassification
import gradio as gr
from PIL import Image
import requests


processor = ViTImageProcessor.from_pretrained('google/vit-base-patch16-224')
model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')


def predict(image) :
  inputs = processor(images=image, return_tensors="pt")
  outputs = model(**inputs)
  logits = outputs.logits
  # model predicts one of the 1000 ImageNet classes
  predicted_class_idx = logits.argmax(-1).item()
  return model.config.id2label[predicted_class_idx]




gradio_app = gr.Interface(
  predict,
  inputs=gr.Image(label="Select image for classification", sources=['upload', 'webcam'], type="pil"),
  outputs=gr.Textbox(),
  title="Image Classification",
  live=True,
  allow_flagging="never",
)

gradio_app.launch()