search

TeamHG-Memex / eli5

A library for debugging/inspecting machine learning classifiers and explaining their predictions
http://eli5.readthedocs.io
MIT License
2.74k stars 332 forks source link

Explain CNN+LSTM Classification #357

Open gabarlacchi opened 4 years ago

gabarlacchi commented 4 years ago

Hi! I am developing a clip classificator using features (extracted from a CNN) fed into an LSTM for classification. It's an end-to-end system. I would like to know if it's possible apply eli5 visualization tool to such a network in order to display, at each classification, the area into the images of the clip that has been "important" for classify if. Someone has already implemented such a system? Thanks in advance, Gabriele

teabolt commented 4 years ago

Hi @barloccia, ELI5 can highlight what's important in an image for Keras CNN's, https://eli5.readthedocs.io/en/latest/tutorials/keras-image-classifiers.html. Support for LSTM's and other libraries is still work in progress and not merged https://github.com/TeamHG-Memex/eli5/pull/325, https://github.com/TeamHG-Memex/eli5/pull/327. Regards, Tomas

simplezhang57 commented 4 years ago

how to use "permutation_importance" on keras LSTM to find out feature importance?

gabarlacchi commented 4 years ago

@teabolt Thanks for the reply. I managed to make what desired with CONV-LSTM and visualize the activations through the time.