import streamlit as st
from transformers import pipeline

classifier = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
def main():
    st.title("image-to-text")

    with st.form("image"):
        image = st.file_uploader('Choose a file')
        # clicked==True only when the button is clicked
        clicked = st.form_submit_button("Submit")
        if clicked:
          results = classifier([image])
          st.json(results)
from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer

model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
def predict_step(image_paths):
  images = []
  for image_path in image_paths:
    i_image = Image.open(image_path)
    if i_image.mode != "RGB":
      i_image = i_image.convert(mode="RGB")
    images.append(i_image)
  pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
  pixel_values = pixel_values.to(device)
  output_ids = model.generate(pixel_values, **gen_kwargs)
  preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
  preds = [pred.strip() for pred in preds]
  return preds
predict_step(['doctor.e16ba4e4.jpg']

if __name__ == "__main__":
    main()
    
"""'audio-classification', 'automatic-speech-recognition', 'conversational', 'document-question-answering', 'feature-extraction', 'fill-mask', 'image-classification', 'image-segmentation', 'image-to-text', 'ner', 'object-detection', 'question-answering', 'sentiment-analysis', 'summarization', 'table-question-answering', 'text-classification', 'text-generation', 'text2text-generation', 'token-classification', 'translation', 'visual-question-answering', 'vqa', 'zero-shot-classification', 'zero-shot-image-classification', 'translation_XX_to_YY'"""