https://github.com/suragnair/im2latex
An implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem
https://github.com/suragnair/im2latex
attention attention-mechanism deep-learning show-and-tell show-attend-and-tell tensorflow
Last synced: about 1 year ago
JSON representation
An implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem
- Host: GitHub
- URL: https://github.com/suragnair/im2latex
- Owner: suragnair
- Created: 2016-12-10T07:55:22.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2016-12-11T10:44:36.000Z (over 9 years ago)
- Last Synced: 2025-03-23T21:45:49.010Z (over 1 year ago)
- Topics: attention, attention-mechanism, deep-learning, show-and-tell, show-attend-and-tell, tensorflow
- Language: Python
- Size: 58.6 KB
- Stars: 17
- Watchers: 4
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Im2LaTeX
An implementation of the Show, Attend and Tell (Xu, Kelvin et. al., 2016) paper in TensorFlow, for the OpenAI Im2LaTeX suggested problem.
- The crux of the model is contained in cnn_enc_gru_dec_attn.py that uses the embedding attention decoder from TensorFlow to attend on the output of the CNN.
- test_cnn_enc_gru_dec_attn.py has a method to extract the attention coefficients for each time step, for which I have overwritten some TensorFlow functions from seq2seq.py.
- An example of attention map over an input LaTeX formula image, as the decoder outputs each token.
