20 lines
939 B
Python
20 lines
939 B
Python
import requests
|
|
from PIL import Image
|
|
|
|
from transformers import GPT2TokenizerFast, ViTImageProcessor, VisionEncoderDecoderModel
|
|
|
|
# load a fine-tuned image captioning model and corresponding tokenizer and image processor
|
|
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
|
tokenizer = GPT2TokenizerFast.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
|
image_processor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
|
|
|
|
# let's perform inference on an image
|
|
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
|
|
image = Image.open(requests.get(url, stream=True).raw)
|
|
pixel_values = image_processor(image, return_tensors="pt").pixel_values
|
|
|
|
# autoregressively generate caption (uses greedy decoding by default)
|
|
generated_ids = model.generate(pixel_values)
|
|
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|
print(generated_text)
|