Thanks for sharing! Learned a lot.
But what I want is presenting the interpretation of validation dataset just like plot_top_losses does. So I’ve wrote a similar method to do it called show_top_losses(). I’ve send my PR and waiting for reply. 
Thanks for sharing! Learned a lot.
But what I want is presenting the interpretation of validation dataset just like plot_top_losses does. So I’ve wrote a similar method to do it called show_top_losses(). I’ve send my PR and waiting for reply.