laicsiifes
/

swin-gportuguese-2

vision-encoder-decoder

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

gabrielmotablima commited on Sep 3

Commit

6ba0193

•

1 Parent(s): bf25f40

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -42,9 +42,9 @@ from PIL import Image
 from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
 # load a fine-tuned image captioning model and corresponding tokenizer and image processor
-model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
-tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
-image_processor = AutoImageProcessor.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
 # perform inference on an image
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"

 from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
 # load a fine-tuned image captioning model and corresponding tokenizer and image processor
+model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-gportuguese-2")
+tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-gportuguese-2")
+image_processor = AutoImageProcessor.from_pretrained("laicsiifes/swin-gportuguese-2")
 # perform inference on an image
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"