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

how to use the pretrained 0.75 model #25

Open
mwsunshine opened this issue Dec 9, 2021 · 0 comments
Open

how to use the pretrained 0.75 model #25

mwsunshine opened this issue Dec 9, 2021 · 0 comments

Comments

@mwsunshine
Copy link

hi, here!

first of all, many thanks for your work! It helps a lot for me!

My question is that how could I use your pretrained mobilenetv2_0.75 model? I looked into the model, the channels change from [32 16 24 32 64 96 160 320] to [24 16 24 24 48 72 120 240]. Does this mean as long as I change the input_channel to 24
and
self.cfgs = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 32, 3, 2],
[6, 64, 4, 2],
[6, 96, 3, 1],
[6, 160, 3, 2],
[6, 320, 1, 1],
]
to
self.cfgs = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 24, 3, 2],
[6, 48, 4, 2],
[6, 72, 3, 1],
[6, 120, 3, 2],
[6, 240, 1, 1],
]
everything is ok?

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

1 participant