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

Some questions about ResNet. #3

Open
vaynelau opened this issue Dec 14, 2019 · 1 comment
Open

Some questions about ResNet. #3

vaynelau opened this issue Dec 14, 2019 · 1 comment

Comments

@vaynelau
Copy link

It is a really nice job! We tried to use resnet as a backbone just like what you did in our own experiment. However, it didn't improve performance as we expected and even performed worse than 4-conv. I wonder if there are some tricks when you trained your model with a resnet. Thank you very much.

@mileyan
Copy link
Owner

mileyan commented Dec 17, 2019

Thanks. We actually did not use any trick during training. Could you check whether you use the hyper-parameters as us?
num-classes=64
batch-size=256
split-dir=./split/mini/
lr 0.1
lr-gamma 0.1
optimizer=SGD
meta-val-interval=4
workers=40
meta-val-metric=cosine
arch=resnet10
save-path=./results/mini/softmax/resnet10
scheduler=multi_step
epochs=90

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