Wei Huadong comments

Results 6 comments of


                                            Wei Huadong

RuntimeError: Expected tensor for argument #1 'input' to have the same device as tensor for argument #2 'weight'; but device 1 does not equal 0 (while checking arguments for cudnn_convolution)

Specify a gpu device using 'CUDA_VISIBLE_DEVICES=0'

How do you choose the optimal hyper-parameters?

same question, just do not know how to set weight for different loss

resnet structure seems to be a bit wrong

the inputsize of cifar100 is too small to use 7X7 conv, i got it

resnet structure seems to be a bit wrong

is there any similar modify in other model structure?

collect2: error: ld returned 1 exit status error: command 'g++' failed with exit status 1

same problem,have you solved it? @JiahaoXia

collect2: error: ld returned 1 exit status error: command 'g++' failed with exit status 1

@hetolin @pyni sudo apt-get install libpcl-dev sudo apt-get install python3-pcl I didn't slove the probIem but I try comands above and install suesscsfully. Use the native python of the system...