fujiankuan 5b0c4e1846 first commit 3 years ago
..
sgan 5b0c4e1846 first commit 3 years ago
README.md 5b0c4e1846 first commit 3 years ago
autocompile.sh 5b0c4e1846 first commit 3 years ago
forecast.cpp 5b0c4e1846 first commit 3 years ago
forecast.pro 5b0c4e1846 first commit 3 years ago

README.md

enviroment:

  1. install pip3 sudo apt-get install python3-pip python3-dev
  2. install numpy sudo pip3 install setuptools sudo pip3 install Cython-0.29.21-py2.py3-none-any.whl unzip numpy-1.19.0.zip cd numpy-1.19.0 sudo python3 setup.py install
  3. install torch sudo pip3 install torch-1.1.0-cp36-cp36m-linux_aarch64.whl
  4. test torch python3 >>>import torch >>>print(torch.version) >>>print('CUDA available: ' + str(torch.cuda.is_available()))

run:

  1. 编译forecast生成可执行文件(qmake && make) or (./autocompile.sh);
  2. 命令 ./forecast arg1 arg2 arg3 arg4 (如: ./forecast ra_ca_fusion 24 8 eth_8_model.pt) 参数arg1为监听的共享内存名称,无则默认ra_ca_fusion,预测结果将保存至名为“xxx_forecast“的共享内存; 参数arg2为预测序列数,无则默认预测24个序列; 参数arg3为观察序列数,无则默认观察8个序列; 参数arg4为载入模型文件的名称,无则默认载入eth_8_model.pt。