-
Notifications
You must be signed in to change notification settings - Fork 95
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
请问可以将batchsize设置为大于1吗? #79
Comments
当时这套代码是在3090上跑的,只考虑了每张卡batchsize为1的情况,很抱歉暂不支持多batchsize |
请问主要是哪些因素限制了 bs的设置呢?
…---- 回复的原邮件 ----
| 发件人 | Yi ***@***.***> |
| 日期 | 2023年11月20日 10:36 |
| 收件人 | ***@***.***> |
| 抄送至 | ***@***.***>***@***.***> |
| 主题 | Re: [weiyithu/SurroundOcc] 请问可以将batchsize设置为大于1吗? (Issue #79) |
当时这套代码是在3090上跑的,只考虑了每张卡batchsize为1的情况,很抱歉暂不支持多batchsize
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
同学你改了samples_per_gpu后报什么错 |
RuntimeError: stack expects each tensor to be equal size, but got [40086, 4] at entry 0 and [42776, 4] at entry 1 改了samples_per_gpu=2之后,两个张量在堆叠(stack)操作时的维度不一致。这里的张量指的gt_occ。 |
gt_occ的尺寸不一致,放入同一个batch会报错 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
如何设置呢?我将config文件中的samples_per_gpu参数修改后还是会报错
The text was updated successfully, but these errors were encountered: