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 zfzfdafei
Visitor
238 Views
Registered: ‎06-30-2009

detection performance degrade seriously after Decent quantization

Hi everyone.I have encounter a problem when I use resnet50 as SSD backbone. When I trained the network after 20000 iterations in my own dataset(grayscale,11 classes) the detection eval reach 92%, but when I use Decent quantization, after calibration, the test detect_eval is only 8%. The carlibration dataset have 135 images.

I have use resnet50 as SSD backbone to train VOC dataset before, no such degradation happened in the process of Decent quantization, only +/- 5% around the caffe test result.

I have tried the decent weight_bit data_bit method and calib_iter parameters,but the result is still poor, can anyone tell me the reason?

0 Kudos
1 Reply
Xilinx Employee
Xilinx Employee
188 Views
Registered: ‎05-24-2019

Re: detection performance degrade seriously after Decent quantization

@zfzfdafeiA few suggestions...

[1] Please review jcory's commentary related to batchnorm / scale layers at this post:

https://forums.xilinx.com/t5/Deephi-DNNDK/An-error-about-DNNC/m-p/995277

[2] Please ensure that you are using images from your training set for calibration

[3] If possible, please increase the number of calibration images that you are using to 100 images

--Quenton

0 Kudos