enviroment:
- install pip3
sudo apt-get install python3-pip python3-dev
- 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
- install torch
sudo pip3 install torch-1.1.0-cp36-cp36m-linux_aarch64.whl
- test torch
python3
>>>import torch
>>>print(torch.version)
>>>print('CUDA available: ' + str(torch.cuda.is_available()))
run:
- 编译forecast生成可执行文件(qmake && make) or (./autocompile.sh);
- 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。