-
Notifications
You must be signed in to change notification settings - Fork 48
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
训练问题请教! #64
Comments
请问你实现了效果吗,你使用1000种字体来训练吗。卡住不动很可能是因为电脑不行了阿,batch也大。显卡咋样,电脑咋样呢 |
原因可能是验证的时间花费较高,建议可以将验证关闭或者修改 |
后面直接改成epoch=298的时候让它验证哈哈哈哈,被它搞烦了,验证一次要几天,但是我用的字母和数字训练的,效果.....咋说,不细看是好的,但是有些笔划还是会缺失,甚至生成错误的字,比如说会将N生成H,要不就是风格压根就没变,我用的1000种来进行训练,15种来验证,每一种大概是62个字符图像,batchsize最后我改成32,训练了300个epoch,每个epoch迭代1313次。但是效果差可能是因为我用的DCNv1,论文用的DCNv2,V2装不了我就没用了 |
用的nvidia titan |
如果是字母的话可以迭代少一点次数。此外我们最新的论文DG-Font++能够有效地解决某些风格生成不好、笔画缺失等问题。 |
运行两个epoch之后,好像进入了验证模式?生成了一些图片,但是现在卡住不动了,也没有报错信息,想问问有什么好的解决方案吗?这时我设置的运行时的命令:
python main.py --gpu 0 --img_size 80 --data_path --output_k 1000 --batch_size 42 --val_num 20
thanks!
The text was updated successfully, but these errors were encountered: