The codes stuck when import encoding

[dreamPoet]

Hi,

I have tried gcc version 4.9.4, 5.3.0, 5.4, 7.3.0 but my codes stuck in import encoding without giving any error message.

I use python 3.6 and the lib version I used are:

cffi            1.11.5             
chardet         3.0.4              
cycler          0.10.0             
decorator       4.4.1              
idna            2.8                
imageio         2.5.0              
kiwisolver      1.1.0              
matplotlib      3.1.1              
networkx        2.4                
ninja           1.9.0.post1        
nose            1.3.7              
numpy           1.15.2             
opencv-python   3.4.4.19           
Pillow          6.0.0              
pip             19.3.1             
protobuf        3.11.1             
pyparsing       2.4.5              
python-dateutil 2.8.1              
PyWavelets      1.0.3              
PyYAML          3.13               
requests        2.22.0             
scikit-image    0.15.0             
scipy           1.2.0              
setuptools      42.0.2.post20191203
six             1.13.0             
tensorboardX    1.9                
torch           1.1.0              
torch-encoding  1.0.1              
torchvision     0.2.0              
tqdm            4.28.1             
urllib3         1.25.7             
wheel           0.33.6 

Thank you very much!

[HAOCHENYE]

https://github.com/nv-tlabs/GSCNN/issues/34#issuecomment-564370469 You can try it

[dreamPoet]

#34 (comment) You can try it

thx it's a good idea...but how about the parameters sync. when training on multi GPU? Will it cause problem?

[shabnambanu1983]

I initially faced this issue but later I solved as follows:

--Using a 2 GPU machine --Installed all the required drivers and cuda tool kits --checked all GPUs are visible --Installed pytorch GPU version. As pytorch does not support cuda 11.0 as of now so I had to build it from source --pip install encoding [ final step] . [Its compulsory ] After this import encoding worked perfectly

Thanks, Shabnam