Closed baolinhu closed 5 years ago
It could be of 2 reasons for slow rate, 1 is your input image size.. and second is your backbone network. I tried with vgg16 as backbone, speed was 2.3 samples/sec with resent 50, speed is 2.5 samples/sec But with resnet 18 , speed is 6.2 samples/sec. I am using aws instance p2.large.. single GPU.
It is possible if your dataset has much more objects in one image. Speed is slower most likely due to symdata.bbox_overlaps function, where v5.1 release had a Cython extension.
@ijkguo You are right.My dataset has much more objects than voc or coco.It means I should use the v5.1 ,not the latest version? Thanks.
Unfortunately yes for now. v6 is nothing better than v5, except simpler usage and less code.
Training with VOC data sets, 5.5imgs/second
Using your own dataset (converted to VOC format), only 1.7imgs/second
It's all 4 1080Ti, and the parameters are the same.