RTX2080Ti 配置maskrcnn

官方安裝教程！

RTX2080TI

首先請務必查看我的博客。這是個大坑，搞了三天cuda版本，最後諮詢官方纔得以解決。

這些是必須的要求（強烈建議linux，win10安裝失敗！）

GCC >= 4.9
CUDA >= 9.0

安裝流程

export TORCH_CUDA_ARCH_LIST=“7.0” （terminal裏敲）
然後
python setup.py build develop
我的說明在字裏行間，請大家一步一步照做！

# first, make sure that your conda is setup properly with the right environment
# for that, check that `which conda`, `which pip` and `which python` points to the
# right path. From a clean conda env, this is what you need to do

conda create --name maskrcnn_benchmark -y
conda activate maskrcnn_benchmark

# this installs the right pip and dependencies for the fresh python
conda install ipython pip

# maskrcnn_benchmark and coco api dependencies
pip install ninja yacs cython matplotlib tqdm opencv-python

# follow PyTorch installation in https://pytorch.org/get-started/locally/
# we give the instructions for CUDA 9.0
------------------------------分割線----------------------------------------
# 改成10，不然rtx不兼容
conda install -c pytorch pytorch-nightly torchvision cudatoolkit=10.0

export INSTALL_DIR=$PWD

# install pycocotools
cd $INSTALL_DIR
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
python setup.py build_ext install

# install cityscapesScripts
cd $INSTALL_DIR
git clone https://github.com/mcordts/cityscapesScripts.git
cd cityscapesScripts/
python setup.py build_ext install

------------------------------分割線----------------------------------------
這塊的就開始有問題了，因爲首先apex沒有windows支持，win 用戶自閉。其次請確認gcc與g++版本，4.9最好，
不會調整版本參考[我的博客](https://blog.csdn.net/qq_39575835/article/details/102547095)
# install apex
cd $INSTALL_DIR
git clone https://github.com/NVIDIA/apex.git
cd apex
------------------------------分割線----------------------------------------
# 如果下面語句出錯請輸入：python setup.py install
python setup.py install --cuda_ext --cpp_ext

# install PyTorch Detection
cd $INSTALL_DIR
git clone https://github.com/facebookresearch/maskrcnn-benchmark.git
cd maskrcnn-benchmark

# the following will install the lib with
# symbolic links, so that you can modify
# the files if you want and won't need to
# re-build it
------------------------------分割線----------------------------------------
# 如果下面語句出錯請在terminal輸入：export TORCH_CUDA_ARCH_LIST="7.0"
python setup.py build develop


unset INSTALL_DIR

# or if you are on macOS
# MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ python setup.py build develop