Kernel Head in RTMDET
#10032
Replies: 1 comment 1 reply
-
|
@GTrui6 Its a reference from condinst, you can see the original paper |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
Thanks for your reply, i have saw the paper |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Why the kernel head in RTMDET has 169 dimensions? The paper says:"The vector is divided into three parts (lengths are 88, 72, and 9 respectively), which are used to form the kernels of three dynamic convolution layers". So why is that?
Beta Was this translation helpful? Give feedback.
All reactions