Skip to content
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

YOLOv5网络修改 #1

Open
sunshine411 opened this issue Aug 31, 2020 · 1 comment
Open

YOLOv5网络修改 #1

sunshine411 opened this issue Aug 31, 2020 · 1 comment

Comments

@sunshine411
Copy link

sunshine411 commented Aug 31, 2020

你好, 我最近两天也在使用tensorflow重新实现网络, 现在还没有完成, 刚看到你的代码, 有两点疑问:

  1. 你代码中是否缺少focus层;
  2. 根据pytorch源码, 我记得有些层既没有bn, 也没有bias.

`def focus(input_data, trainable, init_width_size):
input_data = tf.concat([input_data[:, ::2, ::2, :], input_data[:, 1::2, ::2, :],
input_data[:, ::2, 1::2, :], input_data[:, 1::2, 1::2, :]], 3)
input_data = conv(input_data, (3, 3, 12, init_width_size), trainable=trainable, name='conv0', act_fun='mish')
return input_data

`

感谢您的分享.

@ycdhqzhiai
Copy link
Owner

1.你好,readme里面提到过,我去除了focus slice,直接用strides=2取代了
2.完全按照原版里面,没BN的话,训练在第二个epoch loss就为na了,所以我BN统一设置为True

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants