search

huoyijie / AdvancedEAST

AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.https://github.com/huoyijie/raspberrypi-car
https://huoyijie.cn/
MIT License
1.23k stars 380 forks source link

为何在ICDAR2015训练 val_loss0.73就再也下不去了？ #81

Open lijian10086 opened 5 years ago

lijian10086 commented 5 years ago

image 使用默认参数训练736的模型，ICDAR2015的1000张图片，train=9:val=1,val_loss很快过拟合，版主有遇到过么？如何解决？@huoyijie

lijian10086 commented 5 years ago

train-loss=0.41

Zhang-O commented 5 years ago

大哥 你是拿着预训练模型 接着训练的吗

isyanan1024 commented 5 years ago

@lijian10086 请问训练的时候cuda和cudnn版本是多少，一直提示 Loaded runtime CuDNN library: 7600 (compatibility version 7600) but source was compiled with 7102 (compatibility version 7100). If using a binary install, upgrade your CuDNN library to match. If building from sources, make sure the library loaded at runtime matches a compatible version specified during compile configuration.

wsy915 commented 5 years ago

@lijian10086 请问你的这个问题解决了吗，我用主页给的这10000个样本的数据集跑，也出现这个问题。在epoch=12就停止了

v-smwang commented 5 years ago

+1

xiulianzw commented 5 years ago

@lijian10086 请问训练的时候cuda和cudnn版本是多少，一直提示 Loaded runtime CuDNN library: 7600 (compatibility version 7600) but source was compiled with 7102 (compatibility version 7100). If using a binary install, upgrade your CuDNN library to match. If building from sources, make sure the library loaded at runtime matches a compatible version specified during compile configuration.

你升级一下tensorflow-gpu的版本，装个1.8的试试