RichardMrLu

emmm, after I run 'python main.py -sr --s 0.0001', my checkpoint.pth.tar is 153M... Can you help me? Thanks.

And it didn't save model_best.pth.tar...

I check it, because of pytorch0.4, after test,type(prec1) is Tensor, so change it to type int. But models are still 153M....

@MrLinNing Hello, I only change dataset's path to own Cifar10, how do you save so small model? Thanks for your help.

Parameters are 20M, so model size should be (20x1000000x32)/(1024x1024x8)=76.29M soga

@Coderx7 def test(): model.eval() test_loss = 0 correct = 0 for data, target in test_loader: if args.cuda: data, target = data.cuda(), target.cuda() data, target = Variable(data, volatile=True), Variable(target) output =...

@noUmbrella after your solved this bug, do you work well? what is your mAP?

@noUmbrella = = sorry, I didn't run the code.

@pgadosey Hi, do you find the method to save the quantized model's params? I try to do some quantization , but the model's size unchanged, could you help me? I...

In traditional quantization, like linear quantization, it works on two stage, first map input to integer index, then map integer index to the output(approximation of input). Maybe save the paramers...