Installation of EfficientPS not working due to dependency inplace_abn (inplace_abn not updated for CUDA Driver Version 11)

[StephenHausler]

Hi,

I am currently attempting to install your code, however I am unable to get the requirement inplace_abn installed. I'm running Ubuntu 18.04.
I followed your instructions: I created a new conda environment using your environment.yaml file and also installed

• cudatoolkit=10.2
• pytorch=1.7.0
• torchvision=0.8.0
  I also had to uninstall "typing" from pip to progress past an error (https://stackoverflow.com/questions/55833509/attributeerror-type-object-callable-has-no-attribute-abc-registry). With typing installed, a get an error: "AttributeError: type object 'Callable' has no attribute '_abc_registry'

My current error is with the dependency inplace_abn, which from my reading of their issues list lacks support for CUDA Driver Version 11. I'm currently using CUDA Driver Version 11.4. My error is a compilation error attempting to install inplace_abn (I'm reluctant to change my CUDA driver version due to other dependencies in my project).

My question is, will your network run without inplace_abn at inference time only, with code modifications? (or will the different BN scaling parameters ruin the network performance if inplace_abn is removed and replaced with traditional BN)

[srimannarayanabaratam]

Did you check for the typing versions installed in your environment? I had the same problem (but while building pycocotools) and found that there are two versions of typing: 3.7.4.3 and 3.10.0.2. So, I removed the 3.7.4.3 using pip uninstall and could build inplace-abn and pycocotools successfully. However, my cuda driver version is 10.1.