718c41634f
1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试 2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程 3.重整权利声明文件，重整代码工程，确保最小化侵权风险 Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c |
||
|---|---|---|
| .. | ||
| readme.txt | ||
You can find pytorch2ncnn tool here https://github.com/starimeL/PytorchConverter https://github.com/inisis/brocolli For newer version, pytorch already supports exporting to onnx out of box You can follow the practical guide here https://github.com/Tencent/ncnn/wiki/use-ncnn-with-pytorch-or-onnx