New issue

Jump to bottom

关于fine-tuning_using_pre-trained网络冻结 #3

Open

HeXu1 opened this issue Mar 12, 2018 · 1 comment

HeXu1 commented Mar 12, 2018

for layer in model.layers[:25]:
layer.trainable = False

兄台这个是将25层之前的全部冻结，你的readme里说将最后一层冻结。。。友情提醒一下你分享的这个资源挺好的谢谢

yuyifan1991 commented Jul 24, 2018 •

edited

Loading

我在运行fine-tuning_using_pre-trained.py时报错：KeyError: "Can't open attribute (can't locate attribute: 'nb_layers')"。什么原因，怎么解决。感谢了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment