alexandrosstergiou / adapool

[T-IP 2023] Code for exponential adaptive pooling for PyTorch

Hi there

I am an Assistant Professor at University of Twente's Data Management & Biometrics (DMB) group. Previously, I was a Postdoc at VUB and a Research Associate at the University of Bristol working with Dima Damen on video understanding. I obtained my PhD from Utrecht University where I was lucky to be supervised by Ronald Poppe and Remco C. Veltkamp. My thesis was on human action and interaction recognition in everyday social settings. During my time in Utrecht, I additionally worked on improving the efficiency and interpretability of spatiotemporal deep learning video classification models.

adapool's Issues

Solution: Unresolved extern function '_Z3powdi'”

cuda11. 0

When I tried to build your project on win10, I encountered the following problems：
“ptxas fatal : Unresolved extern function '_Z3powdi'”

Reason: Wrong use of pow function in Cu code
Solution: for example, pow (x, 2) can be changed to X * X

pytorch

can adapool function completely implement in torch，without any cpp

Does AdaPool2d's beta require fixed image size?

I'm currently running AdaPool2d as a replacement of MaxPool2d in Resnet's stem similar on how you did it in SoftPool. However, I keep on getting an assertionError in line 1325 as shown below:

assert isinstance(beta, tuple) or torch.is_tensor(beta), 'Agument `beta` can only be initialized with Tuple or Tensor type objects and should correspond to size (oH, oW)'

Does this mean beta requires a fixed image size, e.g. (224,244)? Or is there a way to make it adaptive across varying image size (e.g. object detection)?

how to use it in yolov5

can you share the code for object detection?

The version of pytorch and how to deal with `nan_to_num` function in lower versions

Thank you for this amazing project. I saw it from SoftPool.
After installing it, make test, but I got AttributeError: module 'torch' has no attribute 'nan_to_num', after I checked, this function used in idea.py was introduced in Pytorch 1.8.0, so the torch version in the README may need to be updated, or is there an easy way to be compatible with lower versions?

How to set the beta?

Hi, thanks for your nice work! However, I am confusing on how to set the beta

你好

你好，可以提供Python版本的代码吗 谢谢

About Adaptive Pool 2d

Installation issue on Google Colab

Hi,
Thanks for providing a Cuda optimized implementation. While building the lib I encountered an issue with "inf" at limits.cuh.

CUDA/limits.cuh(119): error: identifier "inf" is undefined

CUDA/limits.cuh(120): error: identifier "inf" is undefined

CUDA/limits.cuh(128): error: identifier "inf" is undefined

CUDA/limits.cuh(129): error: identifier "inf" is undefined

4 errors detected in the compilation of "CUDA/adapool_cuda_kernel.cu".
error: command '/usr/local/cuda/bin/nvcc' failed with exit status 1
Makefile:2: recipe for target 'install' failed
make: *** [install] Error 1

The following notebook provides more details with environment informations:
https://colab.research.google.com/drive/1T6Nxe2qbjKxXzo2IimFMYBn52qbthlZB?usp=sharing

CAN

Can I use it in kaggle?