FusedBatchNormV3 support

1. tensorflow MUST is 1.13.x
2. keras.backend.set_learning_phase(0) before create tf session !

BTW, you are so lucky, because I have tried lanenet last year...
https://github.com/rknn-demos/lanenet-lane-detection

kaishi 发表于 2020-3-24 13:39
I install tensorflow=1.13.0 and it works now.
However, it is quite slow on rk3399pro. The rknn_perf  ...

Yes, it is a perf without quantization.
You must set do_quantization=True, and run again.

cfan 发表于 2020-12-23 11:49
我在你的代码中看到有这么一句话，
# Workaround RKNN 1.1.0 bug
想问问是遇到了什么样的bug。

这个bug早在1.2.0就解决了。。。

cfan 发表于 2020-12-24 13:53
再问一下，我把模型用一张图片进行量化之后速度达到7帧左右，还有什么办法能提高速度吗
...

可以进置顶帖qq群里跟他们讨论下。