sunrise666

[email protected]

China University of Geosiences China(WuHan)

Results 2 comments of


                                            sunrise666

the losses function

try to change optimizer and learning_rate and weight_decay,use tensorboard to see how the value affect your loss

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[16,64,300,300] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc

how to solve this problem?