File size: 1,054 Bytes
5fa1a76 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
thon
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)
a cat laying on a blanket next to a cat laying on a bed
Loading a PyTorch checkpoint into TFVisionEncoderDecoderModel. |