flax-community
/

Image-captioning-Indonesia

Text2Text Generation

clip-vision-marian

Inference Endpoints

Model card Files Files and versions Community

Galuh commited on Jul 17, 2021

Commit

e7539a3

•

1 Parent(s): 5948cd7

Update README.md

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -13,9 +13,7 @@ At time of writing, you will need to install [HuggingFace](https://github.com/hu
 You will also need to have the [`flax_clip_vision_marian` folder](https://github.com/indonesian-nlp/Indonesia-Image-Captioning/tree/main/flax_clip_vision_marian) in your project directory to load the model using the `FlaxCLIPVisionMarianForConditionalGeneration` class.
-Assuming that you have image bytes as input:
-```
 from torchvision.io import ImageReadMode, read_image
 from torchvision.transforms import CenterCrop, ConvertImageDtype, Normalize, Resize
 from torchvision.transforms.functional import InterpolationMode

 You will also need to have the [`flax_clip_vision_marian` folder](https://github.com/indonesian-nlp/Indonesia-Image-Captioning/tree/main/flax_clip_vision_marian) in your project directory to load the model using the `FlaxCLIPVisionMarianForConditionalGeneration` class.
+```python
 from torchvision.io import ImageReadMode, read_image
 from torchvision.transforms import CenterCrop, ConvertImageDtype, Normalize, Resize
 from torchvision.transforms.functional import InterpolationMode