UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
Visitor lixun123
Visitor
682 Views
Registered: ‎09-29-2018

I need help on adas_detection

Hi!

I want to run my own training YOLO V3 model on ZCU102 or Ultra96 boards, but there is no detailed introduction in the DNNK user guide. I have some questions at present: 1. There are some layers in Yolo V3 that Caffe does not support. Is the model trained with caffe? Can you provide detailed steps?

Thank you!

0 Kudos
6 Replies
Visitor lixun123
Visitor
638 Views
Registered: ‎09-29-2018

Re: I need help on adas_detection

Can someone help me?

0 Kudos
Explorer
Explorer
567 Views
Registered: ‎10-24-2008

Re: I need help on adas_detection

@lixun123YOLOv3 is trained using DarkNet and then deployed using a DarkNet to Caffe model conversion tool.  To the best of my knowledge, the layer support for YOLOv3 is already in place and it can be directly deployed using this flow.  I would suggest that this discussion might be best driven outside of the forums.  I will send you a PM and we can try to connect you with the right team members.

--Quenton

0 Kudos
Observer lucc1
Observer
457 Views
Registered: ‎01-23-2019

Re: I need help on adas_detection

Also interested in doing this:

1- Training from Darknet (yolov3 or yolov3-tiny)

2- Darknet to Caffe

3- Caffe to Xilinx

Please also send me information.

--
Luc Chouinard
FPGA Architect & AI Specialist
Teledyne Imaging
Teledyne Lumenera
0 Kudos
Explorer
Explorer
448 Views
Registered: ‎10-24-2008

Re: I need help on adas_detection

@lucc1I will send you a private message and we will get you connected with the tool.

--Quenton

0 Kudos
Contributor
Contributor
393 Views
Registered: ‎08-09-2018

Re: I need help on adas_detection

@qhall Is there any method to run yolov3 on ZCU102 board with high throughput and speed(like 30fps of yolov3-tiny)? I also wonder if you know how to convert the yolov3 from darknet to caffe while the transformed model can be quantized properly by the Decent tool. I am really confused about this conversion step. And how to solve the quantization of layers which caffe does not support?

0 Kudos
Explorer
Explorer
386 Views
Registered: ‎10-24-2008

Re: I need help on adas_detection

@jsi_wmzAbsolutely.  The ADAS model example is YOLO based.  We can deploy, quantize and prune YOLOv3.  You need the DarkNet to Caffe tool and I will follow-up with you on that topic directly.

--Quenton

0 Kudos