using ./prototxt/face_solver.prototxt & ./prototxt/face_train_test.prototxt but not converge

happynear / AMSoftmax

A simple yet effective loss function for face verification.

MIT License

485 stars 130 forks source link

using ./prototxt/face_solver.prototxt & ./prototxt/face_train_test.prototxt but not converge #12

Closed mingzhang96 closed 6 years ago

mingzhang96 commented 6 years ago

As I don't have enough GPU memory, I set iter_size: 8 in face_solver.prototxt and batch_size: 32 in face_train_test.prototxt, after 30000 iter it didn't converge on CASIA-Webface. I am confused that if I have done anything wrong.

Thanks in advanced.

mingzhang96 commented 6 years ago

Oh it needs two-step train strategy.