pytorch_solov2 icon indicating copy to clipboard operation
pytorch_solov2 copied to clipboard

作者能不能说一说代码还有什么缺陷,方便我们研究补全,谢谢了

Open seekerwmy opened this issue 3 years ago • 3 comments

seekerwmy avatar Dec 22 '21 07:12 seekerwmy

缺陷还挺多的,现在工作比较忙,没时间维护了T_T

  1. 只支持resnet18、resnet34两种backbone的训练和测试.
  2. 不支持多显卡并行训练
  3. 训练和测试的配置项不完整
  4. eval时没有可视化
  5. 导出ONNX的脚本,后续部署流程

shortages:

  1. Only supports Resnet18, Resnet34 backbone to train.
  2. Multi GPU parallel training is not supported.
  3. Incomplete configuration items for training and testing.
  4. visualization
  5. export onnx model

ABlueLight avatar Dec 23 '21 03:12 ABlueLight

@seekerwmy 最好参照官方代码做一个对比:smile:

ABlueLight avatar Dec 23 '21 03:12 ABlueLight

谢谢作者

seekerwmy avatar Dec 23 '21 08:12 seekerwmy