search

jwyang / fpn.pytorch

Pytorch implementation of Feature Pyramid Network (FPN) for Object Detection
MIT License
955 stars 224 forks source link

change anchor size to detect extremely small objects #26

Open KevinQian97 opened 6 years ago

KevinQian97 commented 6 years ago

Hi, sorry to bother you again.. I want to change the anchor size to detect some extremely small objects. So in the faster rcnn version, we can directly change the line args.set_cfgs... in trainval_net.py but when it comes to the fpn version the line turns to args.set_cfgs = ['FPN_ANCHOR_SCALES', '[32, 64, 128, 256, 512]', 'FPN_FEAT_STRIDES', '[4, 8, 16, 32, 64]', then when I change the scales and strides, there is a problem about IndexError: list index out of range So does that mean I can only change the anchor size for RPN in config.py?

Thanks for your help

E-Dreamer-LQ commented 5 years ago

I have the same problem

cjxnew commented 3 years ago

I think the key cause the error is not anchor_scales, but images load cache, do you check the path '...../data/cache' and make sure this folder is empty?