GuHuangAI comments

Results 29 comments of


GuHuangAI

cd nms; python setup_linux.py build_ext --inplace; rm -rf build; cd ../../ Traceback (most recent call last): File "setup_linux.py", line 56, in <module> CUDA = locate_cuda() File "setup_linux.py", line 44, in locate_cuda raise EnvironmentError('The nvcc binary could not be ' OSError: The nvcc binary could not be located in your $PATH. Either add it to your path, or set $CUDAHOME

i miss the same error. Could you please tell me how to solve it?

cd nms; python setup_linux.py build_ext --inplace; rm -rf build; cd ../../ Traceback (most recent call last): File "setup_linux.py", line 56, in <module> CUDA = locate_cuda() File "setup_linux.py", line 44, in locate_cuda raise EnvironmentError('The nvcc binary could not be ' OSError: The nvcc binary could not be located in your $PATH. Either add it to your path, or set $CUDAHOME

I solved the problem by reinstalling CUDA10.0,hope its useful

训练的过程Accuracy都显示为0

我这边测试coco的时候 acc也显示为0，请问怎么解决

How to calculate the beat of dance ~

> @WilliammmZ The evaluation code is released, you can use the style classifier trained by our code to extract the feature vector to calculate automatic metrics. Excuse me, could you...

Segmentation fault (core dumped)

My environment: CUDA 10.1 Pytorch 1.3.0

Segmentation fault (core dumped)

Python 3.7.4 GCC 7.3.0

Segmentation fault (core dumped)

> @GuHuangAI are you able to compile and run other Pytorch libraries using native extensions, e.g. by following this tutorial: https://pytorch.org/tutorials/advanced/cpp_extension.html (using the first option, i.e. the setup.py one listed...

Segmentation fault (core dumped)

OK ths。 i will try

Segmentation fault (core dumped)

有两种方案，第一种版本问题，你看一下匹配上，第二种就是用pytorch自带的同步bn，百度一下怎么用------------------ 原始邮件 ------------------ 发件人: "LHeng"

Segmentation fault (core dumped)

我有点忘了版本，不过pytorch0.4 版本的应该是没问题的 ------------------ 原始邮件 ------------------ 发件人: "LHeng"