jiangziya

Results 3 comments of jiangziya

Is it possible to use smaller GPU for inference?

@lijiannuist My gpu is 8G，how can i solve the error "RuntimeError: CUDA out of memory "? error log is: traceback (most recent call last): File "demo.py", line 248, in test_oneimage()...

Is it possible to use smaller GPU for inference?

> > Hi @cqlyiyeshu > > I think that 16G is enough. > > you can try to use less scale in demo.py. especially for 2x. > > @lijiannuist Do...

I use your train.prototxt to train face landmark with caffe. the loss converge to landmark mean value and not change. how to solve this problem. thx.

I have the same problem.