actnn

actnn copied to clipboard

Does this work for any model with activation function as relu?

4

Hello, I'm trying to use the actnn with maddpg (an MARL algorithm). The model just has 3 layers with activation function relu. If so, can you let us know if...

kailashg26

When I intalling actnn on ubuntu18.04, something wrong with it.

3

When I intalling actnn on ubuntu18.04, something wrong with it. ` /usr/local/cuda-10.1/bin/nvcc -I/home/zhaofy/anaconda3/envs/actnn/lib/python3.8/site-packages/torch/include -I/home/zhaofy/anaconda3/envs/actnn/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/zhaofy/anaconda3/envs/actnn/lib/python3.8/site-packages/torch/include/TH -I/home/zhaofy/anaconda3/envs/actnn/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-10.1/include -I/home/zhaofy/anaconda3/envs/actnn/include/python3.8 -c actnn/cpp_extension/minimax_cuda_kernel.cu -o build/temp.linux-x86_64-3.8/actnn/cpp_extension/minimax_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc"...

zhaofangyuan98

I used Actnn in Deeplab v3 plus ResNet50, and the it degrade the iou by %2

9

hewiew

No offense, could you comment on the code? It's really hard to read the source code

Harr7y

Hello, thanks for your work. I tried actnn in ubuntu, it was worked. But when it was used in windows 10, I get a error. Could you please help me...

ElegantLee

There is something wrong with loss.backward()

2

I just modify the model by model = actnn.QModule(model) After that, something wrong happened as follows: Traceback (most recent call last): File "train.py", line 336, in main() File "train.py", line...

Harr7y

How to use it for GANs

1

Thank you for sharing your great work! Can actNN be used for GAN models? I used actNN with the following GAN architecture, but I got the error. https://github.com/knazeri/edge-connect ``` Traceback...

naoki7090624

fix bug in torch._six #15

liuyanyi

not support ceil_mode

1

RuntimeError: Expected ceil_mode == false to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

zimenglan-sysu-512