Q-engineering
Q-engineering
I'v never tested the project with OpenCV 3.6, only with version 4.x in Code::Blocks. Clion software surely must do the job also. In fact the whole cpp is not really...
Sorry to hear. NAN indicates an illegal floating-point operation. Think of a division by zero, or in case of this example a log of zero. The log is taken at...
@kevinzezel, It is possible. However, it involves (a lot off) additional coding. You need to declare a massive array of floats containing all the models' floats. It must be hard-coded...
W've use gcc 8.3.0 with Raspberry Pi 4 and Jetson Nano. Both no problem. OpenCV with CUDA (GPU) on the Jetson Nano, without GPU on the RPi 4. Your NAN...
Which Ubuntu? On a Raspberry Pi 4 installed? Or on a x86_64 machine?
Fixed bug causing the NAN output. 
Indeed, I think it must be the compiler. You name it.
Did you initialize the camera before use? It is done by the command `$ sudo media-ctl --device /dev/media1 --set-v4l2 '"ov5640 2-003c":0[fmt:YUYV8_2X8/ x ]'` Please, read more in the last section...
Dear @MyraBaba, I haven't done any benchmarking between onnx and ncnn models, nor between ram and CPU, because of the many other projects here in the office.
Please find the Python3.6 wheel (tensorflow-2.2.0-**cp36**-cp36-linux_**aarch64**.whl) at our 64 bit section. https://github.com/Qengineering/TensorFlow-Raspberry-Pi_64-bit