Q-engineering
Q-engineering
More people asked the same question. Up till now, we haven't found the time to write a decent guide on transfer training a TensorFlow SSD. Sorry. However, on the internet,...
I have used the models from the official site without bothering to convert them. [TensorFlow Lite models](https://www.tensorflow.org/lite/guide/hosted_models)
@programmeddeath1, We are aware of the issue and addressing it.
Not yet. To be honest, I'm very busy with other projects. In the coming months I do no have any time to address this issue.
Take a look here: https://github.com/airockchip/rknn_model_zoo
OK. This can also be [a candidate](https://github.com/rockchip-linux/rknpu2/tree/master/examples/rknn_yolov5_demo/model/RK3588). I'm also not sure after all this time.
Indeed I found a ready-made one. Main.cpp is more or less a copy of the given example by Radxa
Did you see [this video](https://www.youtube.com/watch?v=pN8mKZ5wpdQ) from a colleague?
@yrik , At this very moment we're working on it!
@zylo117 You're missing the point here. It is not a comparison between RPi and Nano. The RPi has a **lower** FPS **with Vulkan** than without. To make sure that the...