Questions about CotLayer's parameters and computational complexity
dangf15 opened this issue · 1 comments
dangf15 commented
Thank you for the open-source code. Do you have a comparison of the parametric size of conv2d and cotlayer when the kernel size are the same? How do you calculate the number of parameters and MACs of the local conv in cotlyaer?
Looking forward to your reply！
YehLi commented
The kernel sizes of conv2d and cotlayer are both 3*3. You can refer to Table 6 for the comparison. The parameters and flops are calculated by utils/flops_counter.py (get_model_complexity_info).