【已解决！】RKNN转换Tensorflow官方的Deeplabv3后inference结果不

问题已经解决了，原因是中间层的输出是channel first的，所以reshap的时候需要注意。

raul 发表于 2019-3-5 16:17
谢谢反馈，我这里复现下。

顺便一说，我在这里调出了第一层conv(MobilenetV2/Conv/Conv2D)的结果，发现已经不对了。
然后我尝试避免使用rknn自带的图像归一化，直接用 (0. 0. 0. 1.0)，然后自己把图像转成np.float32，再自己做归一化，结果inference的时候出现了segmentation fault不知道为什么，np.float16也不行。
我的quantization一直都没开。
有没有其他什么办法能调出rknn归一化后输入网络之前的数据么？

raul 发表于 2019-3-5 16:17
谢谢反馈，我这里复现下。

你好，问题已经解决了，原因是中间层的输出是channel在前面的，所以最后的输出reshape不应该是1, 65, 65, 21, 而应该是1, 21, 65, 65。然后再np.transpose成 1, 65, 65, 21进行处理。

非常感谢大家的帮助！

chuyee 发表于 2019-3-8 07:56
What's the inference time do you get for DeepLabv3? Is it possible for less than 1s?

Deeplabv3+ is not actually as computation intensive as you think of. Depending on your network architecture, you can run mobilnetv2_dm0.5 up to 15 fps with input size of 513x513.

chuyee 发表于 2019-3-12 16:55
I answer it myself, dm stands for depth multiplier. 0.5 means halve the number of channels used in ...

Yep, the first frame cannot represent general runtime on tensorflow framework. Even if you use dm=1.0 and add aspp and decoder, you can still run it with 10 fps with input size of 513x513, pretty amazing.

chuyee 发表于 2019-3-13 15:29
Here is my deeplabv3 result on 3399pro. I only get 3FPS. I'm using the rknn model converted from dee ...

depends on what input / output node are you using, and whether you quantize your model.

chuyee 发表于 2019-3-26 03:56
@protossw512, see my bug report for rknn.perf_eval() on http://t.rock-chips.com/forum.php?mod=view ...

I am pretty sure, since after tested on Python with official mobilenet deeplabv3 I switched to C++ and use native C++ code evaluated the performance on my own deeplabv3.
In addition to official mobilenet version, I added decoder and aspp modules, which brings additional operations and input size of 400x400. I am able to run it with 9.x FPS.
I also find using node argmax is pretty slow, so I used biasAdd as output, and write my own implementation on C++ to get segmentation result.