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
作者你好,我在一个20类数据集上进行训练,把batch-size改为4后出现了RuntimeError: batch % im2col_step == 0的错误,错误位置为models/ops/src/cuda/ms-deform_attn_cuda.cu文件的第52行。 排查问题后发现im2col_step=64, batch为20(数据类别)*4=80, 导致经过ms-deform_attn_cuda.cu文件51行的im2col_step=min(batch, im2col_step)后batch % im2col_step == 0为真,从而出错。 由之前测试时batch_size=2, 此时的batch为20(数据类别)*2=40,经过im2col_step=min(batch, im2col_step)后batch % im2col_step == 0为假,程序正常运行,没有出现这个问题。
所以想问下作者,如果为了增加batch_size, 可以把这个im2col_step 变量增大吗,会有什么限制吗?由于目前正在看代码,还未完全理解,希望作者看到能够帮忙解答一下
The text was updated successfully, but these errors were encountered:
,经过im2c
我也遇到了同样的问题,您的回答很有帮助。请问增大im2col_step,对模型有什么影响吗
Sorry, something went wrong.
No branches or pull requests
作者你好,我在一个20类数据集上进行训练,把batch-size改为4后出现了RuntimeError: batch % im2col_step == 0的错误,错误位置为models/ops/src/cuda/ms-deform_attn_cuda.cu文件的第52行。
排查问题后发现im2col_step=64, batch为20(数据类别)*4=80, 导致经过ms-deform_attn_cuda.cu文件51行的im2col_step=min(batch, im2col_step)后batch % im2col_step == 0为真,从而出错。
由之前测试时batch_size=2, 此时的batch为20(数据类别)*2=40,经过im2col_step=min(batch, im2col_step)后batch % im2col_step == 0为假,程序正常运行,没有出现这个问题。
所以想问下作者,如果为了增加batch_size, 可以把这个im2col_step 变量增大吗,会有什么限制吗?由于目前正在看代码,还未完全理解,希望作者看到能够帮忙解答一下
The text was updated successfully, but these errors were encountered: