You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
first , i train my model using original softmax
then, i want to finetune it using a-softmax
i intend to initialize the a-softmax's fc6 layer param using the original softmax, but the log says that they don't have the same number of param blobs, I found that margin inner product layer has no bias param blob.
i tried xavier initialization , but when i freeze the layers before fc6 and only learn fc6, the loss cannot converge .Do i have to relax the lr of the layers before fc6?
The text was updated successfully, but these errors were encountered:
first , i train my model using original softmax
then, i want to finetune it using a-softmax
i intend to initialize the a-softmax's fc6 layer param using the original softmax, but the log says that they don't have the same number of param blobs, I found that margin inner product layer has no bias param blob.
i tried xavier initialization , but when i freeze the layers before fc6 and only learn fc6, the loss cannot converge .Do i have to relax the lr of the layers before fc6?
The text was updated successfully, but these errors were encountered: