Showing results for 
Show  only  | Search instead for 
Did you mean: 
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
Registered: ‎05-24-2019

@zfzfdafeiA few suggestions...

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

[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


0 Kudos