0.10.1a

Add multiple features by claude:

• Improve loading data from npy file to reduce memroy footprint by avoid array copy
• add new de_corr backend using a single linear layer with loss function on covariance matrix, this allows tpcav works at big models
• performance optimization at multiple places

Full Changelog: 0.9.6...0.10.1a

0.9.7

Improve memory usage when evaluating classifier

Full Changelog: 0.9.6...0.9.7

0.9.6

Fix a bug that storing attributed layer in tpcav model causes captum to register hook twice on the same module

Full Changelog: 0.9.5...0.9.6

0.9.5

Now tpcav can take a list of meme files as input, relevant functions have been adjusted

Full Changelog: 0.9.4...0.9.5

0.9.4

Minor bug fix, add drop_last option for iterators and set true to avoid mismatch batch sizes when combining different sources

Full Changelog: 0.9.3...0.9.4

0.9.3

Bug fix

Full Changelog: 0.9.2...0.9.3

0.9.2

Bug fix, improve error handling

Full Changelog: 0.9.1...0.9.2

0.9.1

Add synthetic GC content concepts

Full Changelog: 0.8.6...0.9.1

0.8.6

Small bug fix

Full Changelog: 0.8.5...0.8.6

0.8.5

Bug fixes & Log message improvement

Full Changelog: 0.8.4...0.8.5