adirik commited on
Commit
2b592a0
1 Parent(s): 91391e7
Files changed (2) hide show
  1. app.py +1 -2
  2. assets/.DS_Store +0 -0
app.py CHANGED
@@ -31,8 +31,7 @@ description = """
31
  <p>Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/align">ALIGN</a>,
32
  as introduced in <a href="https://arxiv.org/abs/2102.05918"></a><i>"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision"</i>. ALIGN features a dual-encoder architecture with EfficientNet and BERT as its text and vision encoders, and learns to align visual and text representations with contrastive learning.
33
  Unlike previous work, ALIGN leverages a massive noisy dataset and shows that the scale of the corpus can be used to achieve SOTA representations with a simple recipe.
34
- \n\nALIGN is not open-sourced and the `kakaobrain/align-base` model used for this demo is based on the Kakao Brain implementation that follows the original paper. The model is trained on the open source [COYO](https://github.com/kakaobrain/coyo-dataset) dataset by the Kakao Brain team.
35
- To perform zero-shot image classification with ALIGN, upload an image and enter your candidate labels as free-form text separated by a comma followed by a space.</p>
36
  </div>
37
  </div>
38
  """
 
31
  <p>Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/align">ALIGN</a>,
32
  as introduced in <a href="https://arxiv.org/abs/2102.05918"></a><i>"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision"</i>. ALIGN features a dual-encoder architecture with EfficientNet and BERT as its text and vision encoders, and learns to align visual and text representations with contrastive learning.
33
  Unlike previous work, ALIGN leverages a massive noisy dataset and shows that the scale of the corpus can be used to achieve SOTA representations with a simple recipe.
34
+ \n\nALIGN is not open-sourced and the `kakaobrain/align-base` model used for this demo is based on the Kakao Brain implementation that follows the original paper. The model is trained on the open source [COYO](https://github.com/kakaobrain/coyo-dataset) dataset by the Kakao Brain team. To perform zero-shot image classification with ALIGN, upload an image and enter your candidate labels as free-form text separated by a comma followed by a space.</p>
 
35
  </div>
36
  </div>
37
  """
assets/.DS_Store DELETED
Binary file (6.15 kB)