- Class Activation Maps
- Saliency Maps
- Maximal Activation Image
- Quiver
- TSNE
- Neptune
- Tensorboard
- LIME
- Attention
Install the requirements
pip install -r requirements.txtDownload Twitter Sentiment Dataset from http://thinknook.com/wp-content/uploads/2012/09/Sentiment-Analysis-Dataset.zip
or via
wget http://thinknook.com/wp-content/uploads/2012/09/Sentiment-Analysis-Dataset.zipDownload the pretrained glove model from https://nlp.stanford.edu/projects/glove/ and unpack it to some folder.
Specify the filepaths in read_between_the_tweets.py and train your twitter model by running:
neptune run read_between_the_tweets.py --config neptune_tweet.yamlSpecify the filepaths in see_my_face.py and train your facial recognition model by running:
neptune run see_my_face.py --config neptune_facereco.yamlChange the filepaths in notebooks to the same ones you specified in read_between_the_tweets.py and see_my_face.py .
Thank you all for letting the world use this!
Keras.io https://keras.io/
Keras-vis https://raghakot.github.io/keras-vis/
Neptune http://neptune.deepsense.io/versions/latest/
Eli5 http://eli5.readthedocs.io/en/latest/overview.html
LIME https://homes.cs.washington.edu/~marcotcr/blog/lime/
Quiver https://github.com/keplr-io/quiver
Tensorflow https://www.tensorflow.org/
https://jacobgil.github.io/deeplearning/class-activation-maps
https://arxiv.org/abs/1312.6034
http://p.migdal.pl/2017/01/06/king-man-woman-queen-why.html
https://nlp.stanford.edu/projects/glove/
http://blog.echen.me/2017/05/30/exploring-lstms/
https://github.com/philipperemy/keras-attention-mechanism
https://medium.com/@plusepsilon/visualizations-of-recurrent-neural-networks-c18f07779d56
https://richliao.github.io/supervised/classification/2016/12/26/textclassifier-RNN/
https://arxiv.org/pdf/1409.0473.pdf
https://gist.github.com/wassname/5292f95000e409e239b9dc973295327a
https://gist.github.com/nigeljyng/37552fb4869a5e81338f82b338a304d3
