tortoise comments

Repositories
Issues
Comments

Results 2 comments of


                                            tortoise

For some training details, thank you

尊敬的研究者您好，search的过程，我将三组batchsize缩减为32，将val的batchsize缩减为50，就可以在P100 16G的显卡上进行运行。但是我还是有一个疑问，这个代码的并行计算似乎有点问题，我的服务器有8张P100，但是会出现很明显的报错，导致无法并行(矩阵无法对齐)。在retrain CIFAR10的模型过程中，我出现了以下的报错，请问这个对精度有什么影响吗？ Distinguished Researcher Hello, in the process of search, I have reduced the batchsize of three groups to 32 and the batchsize of Val to 50,...

For some training details, thank you

Distinguished researcher hello, I follow your advice. I replaced the V100 graphics card, but my BATchsize can only be set to 48, but still cannot reach 64. Batchsize, including val,...