image-captioning image-to-text

世萌验证码识别模型,训练集60000张图片,基于vit-gpt2微调

Use in Transformers

from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
import torch
from PIL import Image

model = VisionEncoderDecoderModel.from_pretrained("AIris-Channel/vit-gpt2-verifycode-caption")
feature_extractor = ViTImageProcessor.from_pretrained("AIris-Channel/vit-gpt2-verifycode-caption")
tokenizer = AutoTokenizer.from_pretrained("AIris-Channel/vit-gpt2-verifycode-caption")

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

pred=predict_step(['ZZZTVESE.jpg'])
print(pred) #zzztvese