thank you for the inspired paper and for uploading your code.
Maybe I am overlooking it, but I cannot find the files specifying the class frequencies for the balanced softmax loss. The path to the file is specified in the config:
Am I correct in assuming that the file simply contains the class frequencies and, once converted to a torch tensor, that the indices of that tensor correspond to the class labels?
jiawei-ren
commented
7 months ago
Hi,
thank you for the inspired paper and for uploading your code.
Maybe I am overlooking it, but I cannot find the files specifying the class frequencies for the balanced softmax loss. The path to the file is specified in the config:
https://github.com/jiawei-ren/BalancedMetaSoftmax-Classification/blob/34a61e432881816c2da14d577d6ed63501288f5f/config/CIFAR100_LT/balanced_softmax_imba200.yaml#L6C32-L6C32
and used in the balanced softmax loss function to get the class frequencies:
https://github.com/jiawei-ren/BalancedMetaSoftmax-Classification/blob/34a61e432881816c2da14d577d6ed63501288f5f/loss/BalancedSoftmaxLoss.py#L26-L29
Am I correct in assuming that the file simply contains the class frequencies and, once converted to a torch tensor, that the indices of that tensor correspond to the class labels?