Skip to content

Latest commit

 

History

History
24 lines (17 loc) · 1.36 KB

Fix_Bugs_of_Pytorch_Encoding.md

File metadata and controls

24 lines (17 loc) · 1.36 KB
Raw

Pytorch-Encoding

After installing prerequisites as this instruction, we clone Pytorch-Encoding

# Tested with commit ce461da
git clone https://github.com/zhanghang1989/PyTorch-Encoding.git

Then, according to this issue, replace #include <torch/extension.h> with #include <torch/serialize/tensor.h> in all encoding/lib/*/*.cpp and encoding/lib/*/*.cu files. Also add #include <torch/serialize/tensor.h> to encoding/lib/gpu/operator.h.

The Pytorch-Encoding doc requires python setup.py install. However, it's not necessary. You can just add the package path to $PYTHONPATH or sys.path.

Run the examples

export CUDA_HOME=/mnt/data-1/data/houjing.huang/Software/cuda-9.0
export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:${LD_LIBRARY_PATH}

python scripts/prepare_pcontext.py
python test.py --dataset PContext --model-zoo Encnet_ResNet50_PContext --eval

Misc

  • The default ResNet in Pytorch-Encoding is different than pytorch torchvision. The former provides deep_base, dilation, multi_grid options.