search

kimiyoung / ssl_bad_gan

Good Semi-Supervised Learning That Requires a Bad GAN
MIT License
181 stars 46 forks source link

When running the mnist_trainer.py, aCUDA error: out of memory occurred #10

Open XiaoHao-Chen opened 5 years ago

XiaoHao-Chen commented 5 years ago

The error occurred when running pixlecnn++, specifically in the loop section.My graphics card is GTX 1060 6GB.Is it because the memory is too small

xuyujie2 commented 5 years ago

The error occurred when running pixlecnn++, specifically in the loop section.My graphics card is GTX 1060 6GB.Is it because the memory is too small

i had the same question.have you solve it?

XiaoHao-Chen commented 5 years ago

The error occurred when running pixlecnn++, specifically in the loop section.My graphics card is GTX 1060 6GB.Is it because the memory is too small

i had the same question.have you solve it?

I'm sorry I didn't solve it either. But I found that the problem was in the part that called pixelcnn, where each for loop in pixelcnn called pixelcnn's own convolution operation, causing the model to be loaded into the GPU in every for loop, so the GPU was overloaded. Although I know the problem, I still don't have an effective way to solve it. Do you have any good idea?