evlinzxxx
/

best_model_ViTB16_GPT2

vision-encoder-decoder

image-text-to-text

image-captioning

vision-transformer

Inference Endpoints

Model card Files Files and versions Community

evlinzxxx commited on May 19, 2024

Commit

76816e0

·

verified ·

1 Parent(s): 0d1dd00

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -17,9 +17,9 @@ language:
 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):

 from transformers import VisionEncoderDecoderModel, ViTImageProcessor, GPT2Tokenizer
 import torch
 from PIL import Image
+model = VisionEncoderDecoderModel.from_pretrained("evlinzxxx/best_model_ViTB16_GPT2")
+feature_extractor = ViTImageProcessor.from_pretrained("evlinzxxx/best_model_ViTB16_GPT2")
+tokenizer = GPT2Tokenizer.from_pretrained("evlinzxxx/best_model_ViTB16_GPT2")
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 def show_image_and_captions(url):