zhl98

Results 6 comments of zhl98

Hey, after update the incremental_batch_size to 256 , runned with 1 GPU ,the result is still only 69.50%. ![image](https://user-images.githubusercontent.com/51871747/161416429-414e6b70-546c-479f-8b5f-942269ef4a9d.png) But it does seem that the effect of two GPUs is...

cuda版本有要求么,我发现我在python里可以找到gpu,但在代码运行的时候显示没有cuda ![K55W9$HD68 0RQ9E_IOSD5D](https://user-images.githubusercontent.com/51871747/137626162-cf0a81f3-3aa0-4910-8a21-69f9bee2385f.png)

> > cuda版本有要求么,我发现我在python里可以找到gpu,但在代码运行的时候显示没有cuda ![K55W9$HD68 0RQ9E_IOSD5D](https://user-images.githubusercontent.com/51871747/137626162-cf0a81f3-3aa0-4910-8a21-69f9bee2385f.png) > > codes\options\options.py os.environ['CUDA_VISIBLE_DEVICES'] = gpu_list改成os.environ["CUDA_VISIBLE_DEVICES"] = "0" 另外在运行python test_ClassSR.py -opt options/test/test_ClassSR_SRResNet.yml的时候要对应把test_ClassSR.py执行的部分定义成函数(比如main),然后再放到 if **name**=='**main**': main() 执行,可能是因为windows多进程的问题... 把cuda设备数设为0确实可以这个问题,但是这样会用cpu进行训练而不是GPU

update the vit from fp16 to fp32