Chengfeng Zhou

error MSB3073

2

1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V140\Microsoft.CppCommon.targets(133,5): error MSB3073: 命令“"F:\caffe\caffe-windows-ms\windows\\scripts\BinplaceCudaDependencies.cmd" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\bin" "D:\CUDA\CuDNNv5" false true "F:\caffe\caffe-windows-ms\windows\..\Build\x64\Release\" 1>C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V140\Microsoft.CppCommon.targets(133,5): error MSB3073: :VCEnd”已退出，代码为 1。 ### Your system configuration Operating system:win7 Compiler:vs2015 CUDA...

Inputting an image with zero variance will introduce 'NaN'.

1

https://github.com/megvii-research/tlsc/blob/c5c9bac1557d2f95bf281152f09bda61db578a93/basicsr/models/archs/local_arch.py#L100 It will output negative numbers. That is the reason for 'NaN' for torch.sqrt().

How to use multi-gpu?

1

This program seems to only run on one GPU . Can anyone tell me how to run with multiple GPUs? I have assigned GPU 2 and 3 with instruction "export...

https://github.com/BIT-DA/CIRL/blob/1b50cd605fa1779b4adc739569371d0f19a6bcce/models/classifier.py#L42C8-L44C37

Do you add noise on the background of input images in function '__itensity_normalize_one_volume__'?

2

``` def __itensity_normalize_one_volume__(self, volume): pixels = volume[volume > 0] mean = pixels.mean() std = pixels.std() out = (volume - mean)/std out_random = np.random.normal(0, 1, size = volume.shape) out[volume == 0]...

Why does the activation should product sqrt(2)?

3

https://github.com/tomguluson92/StyleGAN2_PyTorch/blob/37741fbadc59c2fb2613248aa5d74f5b9d66de73/network/stylegan2.py#L95

Questions about your Paper

1

I am trying to reproduce your method in BraTs 2017 Challenge. Can you answer me some questions about it? As you described “ Our network architecture is trained with randomly...