Pytorch 项目 实战

“表面缺陷检测的混合监督：从弱监督学习到完全监督学习”的官方 PyTorch 实现

pytorch-cuda-hpc development

Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learning

采用github上star比较高的一个开源实现https://github.com/yhenon/pytorch-retinanet 在anaconda中新建了一个环境，因为一开始并没有新建环境，在原有的环境里，遇到了pytorch，numpy等版本问题，尤其是一开始用0.1.2版的pytorch，