Intel® Quartus® Prime Software
Intel® Quartus® Prime Design Software, Design Entry, Synthesis, Simulation, Verification, Timing Analysis, System Design (Platform Designer, formerly Qsys)
16556 Discussions

Object detection on DE1/DE10-Nano FPGA SOC

Altera_Forum
Honored Contributor II
1,754 Views

I have re-trained SSD-Mobilenet using Tensorflow framework on my own image dataset and able to use it on Ubuntu/Windows with CPU,GPU. I want to test performance on the FPGA board either DE1/DE10-Nano FPGA SOC. Is it possible to use my pre-trained tensorflow model on these boards ? If possible could you guide the workflow i need to take up to achieve this?

0 Kudos
2 Replies
Altera_Forum
Honored Contributor II
775 Views

Well, the only available open-source OpenCL based FPGA design for CNN inference is pipecnn (https://github.com/doonny/pipecnn

and it only support AlexNet and VGG for now.  

For SSD and MobileNet, you need dilate convolution and separable convolution, neither is supported by PipeCNN. 

Either wait for Intel to release CNN library for FPGA, or implement those missing parts based on PipeCNN (actually I'm also trying to do that).
0 Kudos
Altera_Forum
Honored Contributor II
775 Views

Thanks for suggestion :)

0 Kudos
Reply