We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
prog_bar = tqdm(enumerate(train_data_loader)) 这一行卡住的话,是因为filelists/train.txt, filelists/val.txt, filelists/test.txt没配置好,导致Dataset死循环 现在我也遇到了这个情况,训练集、验证集的全路径写在了trian.txt和val.txt ,类似下面的: /root/workspace/processed_data/train/57f7d1d11ca308f3f24728cb5c930574_15.78_16.16 /root/workspace/processed_data/train/4c3df35b8ffdbd064ce3d00288c0d26a_2.44_2.71 /root/workspace/processed_data/train/f5a9b275800eeaa1561b72f5b412908c_2.88_3.3
/root/workspace/processed_data/val/01b7a9520196fad67d4670fdf85cf59d_1.08_1.32 /root/workspace/processed_data/val/8b57ece4a8a0a07395ec833d712497f6_4.68_5.22 /root/workspace/processed_data/val/ade95c1b7497724a5201de58c7304f59_1.6_1.94 然后说原版的代码处理数据集会死循环,要怎么修改呢?请假大佬
The text was updated successfully, but these errors were encountered:
请教大佬,自从修好了报index error的bug后,prog_bar = tqdm(enumerate(train_data_loader))这一条的进度就没变过
Sorry, something went wrong.
如果是cpu的话会很慢
在__getitem__里所有continue处打断点,然后debug,看进了哪一处。 死循环就是因为while True下都过continue而不走return造成的,原版这样写是为了自动跳过一些没处理好的数据。
是的,在等了一个半小时后,终于进度条动了,1000step后loss从开始的0.7764下降到了0.6998,算正常吗?
如果是cpu的话会很慢 是的,在等了一个半小时后,终于进度条动了,1000step后loss从开始的0.7764下降到了0.6998,算正常吗?
嗯,正常。我gpu运行一天多,跑400000step,loss到0.35左右。
大佬,现在跑完35000step,loss就停在0.694不下降了,是LWR1000数据集不行吗?
No branches or pull requests
prog_bar = tqdm(enumerate(train_data_loader)) 这一行卡住的话,是因为filelists/train.txt, filelists/val.txt, filelists/test.txt没配置好,导致Dataset死循环
现在我也遇到了这个情况,训练集、验证集的全路径写在了trian.txt和val.txt ,类似下面的:
/root/workspace/processed_data/train/57f7d1d11ca308f3f24728cb5c930574_15.78_16.16
/root/workspace/processed_data/train/4c3df35b8ffdbd064ce3d00288c0d26a_2.44_2.71
/root/workspace/processed_data/train/f5a9b275800eeaa1561b72f5b412908c_2.88_3.3
/root/workspace/processed_data/val/01b7a9520196fad67d4670fdf85cf59d_1.08_1.32
/root/workspace/processed_data/val/8b57ece4a8a0a07395ec833d712497f6_4.68_5.22
/root/workspace/processed_data/val/ade95c1b7497724a5201de58c7304f59_1.6_1.94
然后说原版的代码处理数据集会死循环,要怎么修改呢?请假大佬
The text was updated successfully, but these errors were encountered: