Xu Jing zhao
Xu Jing zhao
哈哈
Yes,when I set batch_size to 64,it will not wrong here But sometimes my model likes to increase the loss but not decrease the loss when he reached at 22% accuracy...
> > @Simpatech-app have you rebuiled the code? > > Do you mean by running again sh make.sh???? if so, I already did it and still get this error. Any...
You can do multi process training in Ubuntu without problem. I recommand you using Ubuntu when learning Deeplearning. Due to the pytorch's multi process code , you have to set...
Hi , I think learned by network will be better , but it needs so many equipments , I can't test it .So I set it by hand just for...
> > Hi , I think learned by network will be better , but it needs so many equipments , I can't test it .So I set it by hand...
Everthing exists in `Rand_Augment.py` , I don't delete any content . Sorry , I'm not so understand about your question . Can't you access to the `Rand_Augment.py` ?
Thanks ,I will try them both later. There are two more questions . 1: In your paper section `3.4 SCALABILITY TEST ON THE IMAGENET DATASET` , when use UDA in...
Hi ,man . I can only get a single 2080Ti , the errors say `It requires {GPU: 4.000000}, {CPU: 1.000000} for execution and {GPU: 4.000000}, {CPU: 1.000000} for placement, however...