Sharpiless

运行的命令分别是： ```bash CUDA_VISIBLE_DEVICES=0 python main.py --dataset cifar100 --arch vgg --depth 16 --lr 0.01 ``` ```bash python vggprune_pruning.py --dataset cifar100 --depth 16 --model logs/model_best.pth.tar --save results --num_sample 500 ```

补充 VGG19 on CIFAR100 的结果： ```bash Origin number of parameters: 20070180 => loading checkpoint 'logs/model_best.pth.tar' => loaded checkpoint 'logs/model_best.pth.tar' (epoch 149) Prec1: 0.640100 layer index: 2 total channel: 64 remaining...

Thanks for your reply. One more question, the original paper uses cross entropy loss while your code uses BCE loss. Is that the right thing to do?

There are also some implement details which are different from the original paper. For mnist, the batch in paper is 512 and the lr in generator is 3.0 with 24k...