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
Does mc-loss need more training epoches? #16
Comments
Fine-tune or trained form scratch? |
It's fine-tune using ImageNet pretrained weights (load pretrained parameters except the fc layer and last conv layer which is num_classes*3 channels and 1x1 filter size) following is hyper parameters:
the train dataset size is 65528. and optimizer is using SGD with momentum. Thanks! |
The input of the MC-Loss should be the features before GAP (H>1 and W>1). |
Kurumi233/Mutual-Channel-Loss#5 |
Hi,
I added mc-loss to mnasnet (https://arxiv.org/abs/1807.11626v3) network and train it on a custom fine-grained dataset.
The total epoches is 15, initial LR is 2e-2, and final LR is 1e-5 using cosine LR scheduler.
But the validation accuracy at epoch 15 is 0.62, while the original mnasnet implementation reaches 0.78 val accuracy at epoch 15.
The training epoches in the paper is 300, is this the cause?
(my GPU is slow, so I want to experiment for less epoches to determine whether mc-loss performs good on this dataset)
Thanks for your great work!
The text was updated successfully, but these errors were encountered: