Sample running code
from transformers import VisionEncoderDecoderModel, ViTImageProcessor, GPT2Tokenizer
import torch
from PIL import Image
model = VisionEncoderDecoderModel.from_pretrained("evlinzxxx/my_model_ViTB-16")
feature_extractor = ViTImageProcessor.from_pretrained("evlinzxxx/my_model_ViTB-16")
tokenizer = GPT2Tokenizer.from_pretrained("evlinzxxx/my_model_ViTB-16")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
def show_image_and_captions(url):
# get the image and display it
display(load_image(url))
# get the captions on various models
our_caption = get_caption(model, image_processor, tokenizer, url)
# print the captions
print(f"Our caption: {our_caption}")
show_image_and_captions("/content/drive/MyDrive/try/test_400/gl_16.jpg") # ['navigate around the obstacle ahead adjusting your route to bypass the parked car.']
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.