Hugging Face's logo

laicsiifes
/
swin-distilbertimbau

Image-to-Text
Transformers
Safetensors
Portuguese
vision-encoder-decoder
image-text-to-text
Eval Results (legacy)
Model card Files
xet
 Community
1
gabrielmotablima commited on
Commit
855b3ec
·
verified ·
1 Parent(s): 85cc95f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -40,12 +40,12 @@ Use the code below to get started with the model.
40
  import requests
41
  from PIL import Image
42
 
43
- from transformers import AutoTokenizer, ViTImageProcessor, VisionEncoderDecoderModel
44
 
45
  # load a fine-tuned image captioning model and corresponding tokenizer and image processor
46
  model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
47
  tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
48
- image_processor = ViTImageProcessor.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
49
 
50
  # perform inference on an image
51
  url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 
40
  import requests
41
  from PIL import Image
42
 
43
+ from transformers import AutoTokenizer, AutoImageProcessor, VisionEncoderDecoderModel
44
 
45
  # load a fine-tuned image captioning model and corresponding tokenizer and image processor
46
  model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
47
  tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
48
+ image_processor = AutoImageProcessor.from_pretrained("laicsiifes/swin-distilbert-flickr30k-pt-br")
49
 
50
  # perform inference on an image
51
  url = "http://images.cocodataset.org/val2017/000000039769.jpg"