DBNet.pytorch icon indicating copy to clipboard operation
DBNet.pytorch copied to clipboard

open_dataset.yaml 和 open_dataset_resnest50_FPN_DBhead_pilyLR.yaml 上报错跑不通

Open Xbotgo-Justin1 opened this issue 3 years ago • 1 comments

用icdar2015.yaml 和 icdar2015_resnet18_FPN_DBheead_polyLR.yaml 能跑通的训练集和测试集的结构 放到 open_dataset.yaml 和 open_dataset_resnest50_FPN_DBhead_pilyLR.yaml 上报错跑不通, 请问自定义的配置文件 有样例说明么?

Xbotgo-Justin1 avatar Jan 26 '22 02:01 Xbotgo-Justin1

Simple method Copy icdar2015_resnet18_FPN_DBhead_polyLR.yaml and change the name into icdar2015_resnet50_FPN_DBheead_polyLR.yaml and change line 5 (backbone: resnet50)

problem solve

aswa123 avatar May 17 '22 03:05 aswa123