BIC
BIC copied to clipboard
Training parameters (lr and weight decay) change.
Change the lr schedule from steplr to multistep lr following the paper. Change weight decay according to the incremental stages. Early stages have larger weight decay than late stages. I got one close result [0.856, 0.72125, 0.6556666666666666, 0.6015, 0.5577], see the log file in the folder logs.
The distillation part is also different from our implementation. But I think your implementation is kind of fine.