-
Notifications
You must be signed in to change notification settings - Fork 22
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
为什么7x7的深度卷积可以分解成3x3和1x11和11x1的深度卷积? #3
Comments
Hi @EchoXu98 , Thanks for your attention. "decompose" here is more like "replace" from the aspect of performance. Depthwise convolution and inception depthwise convolution are not mathematically equivalent. |
您好,请问Inception dep. conv中的参数量(2k=9)C/8是怎么计算出来的?Inception dep conv的参数量应该和g的设置有关系吧。 |
Hi @sdu-huanhq , Thanks for your attention. Yes, g is set as 1/8 by default in Table 1. Thanks for your reminder, I will add this information in the table caption in the next revision. |
Thanks for your answer and thumbs up for your work |
Thank you so much! |
I want to know where is the (2k+9) from?I know the C/8 is the parallel channel count |
|
oh,I know it.thank you
…---原始邮件---
发件人: "Weihao ***@***.***>
发送时间: 2023年5月8日(周一) 晚上9:32
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [sail-sg/inceptionnext] 为什么7x7的深度卷积可以分解成3x3和1x11和11x1的深度卷积? (Issue #3)
您好,请问Inception dep. conv中的参数量(2k=9)C/8是怎么计算出来的?Inception dep conv的参数量应该和g的设置有关系吧。 Hello, may I ask how to calculate the parameter number (2k=9)C/8 in Inception dep. conv?
I want to know where is the (2k+9) from?I know the C/8 is the parallel channel count
2k from 1xk conv and kx1 conv and 9 from 3x3 conv.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
您好!我想请问下,就是我标题中的问题“为什么7x7的深度卷积可以分解成3x3和1x11和11x1的深度卷积?” 这种分解是有严格数学推导吗?可以推导出分解前和分解后,二者的卷积核大小相同?还是因为效果好才这样分解?If you don't understand my question, I can ask it in English!
The text was updated successfully, but these errors were encountered: