smilealvin92

Results 6 comments of smilealvin92

> [#236 (comment)](https://github.com/DayBreak-u/chineseocr_lite/issues/236#issuecomment-675221959) 楼主,可以帮帮看一下吗?我这边要C++加载试试模型,C++进行部署测试。但是现在模型无法转换。 这位老师,您的问题解决了吗,我用x86下面的python3.8.13的0.4.1的onnx-simplifier能够实现简化,但是还是有几个胶水op没有解决,大部分胶水op确实去掉了

解决了,可以参考已有 param模型去手动编辑新产生的模型,但是我基于20220721版本的ncnn编译出来的模型,经过修改后,虽然能够加载,但是推理出来的文本是错的,这个目前还没找到原因

> https://github.com/deepinsight/insightface/blob/master/python-package/insightface/utils/face_align.py#L70 Many thanks! You are a good man.

> https://github.com/deepinsight/insightface/blob/master/python-package/insightface/utils/face_align.py#L70 I found that if we had the landmarks, we do not need the location of the face. Only the origin image and landmarks is enough to do the...

哪一款都一样