Roman Solovyev

Can you please create some small example based on your neural net which cause the error? I will fix it then.

Check display connection. If you connected it with wires as in the demo, a bad contact is possible. The voltage on the GPIO is 5 and 3.3V. VCC must be...

Hello. You can find weights file for people here: https://drive.google.com/file/d/1-AtcpEhaiKIGhBVai_X-wendXKEltk1e/view?usp=sharing

We added new python file: https://github.com/ZFTurbo/MobileNet-in-FPGA/blob/master/r08_generate_weights_file_for_FPGA.py It generates weights in needed format.

Also some notes from Alex who did most of work with FPGA: 1) if a yellow inscription appears next to the project navigator when opening a project, you should go...

I have a question. Was you able to run the code successfully on FPGA?

As I remember I keep coefficeints "as is" in this code. But they overflow 7 bits over the 1.0 point. Some note: quantization method used in this project not really...

Actually you use the same conv operations. The only difference that you need to requantize to new scale after layer calculation complete. But it's just single multiplication and shift. In...

No, this variable only controls which GPU use for calculation. Code is for single GPU only. If you need inference on several GPU, just split data in N parts and...

It's very old code. It works with TF 1.* version: Try this settings: ``` tensorflow-gpu==1.15.3 keras==2.2.3 keras-resnet==0.1.0 keras-retinanet==0.4.1 ``` or this - I used in my latest project with given...