YangHM / Convolutional-Prototype-Learning

An implementation (TensorFlow) of CPL and GCPL appeared in CVPR2018 paper: "Robust Classification with Convolutional Prototype Learning"
129 stars 32 forks source link

Initialization Problem #6

Open ForeverPs opened 2 years ago

ForeverPs commented 2 years ago

Thanks for your greate jod. In my experiments, I find it is difficult to converge with prototypes randomly initialized. How can I solve this? I have no prior on the dataset. With a Softmax CNN, the convergence process is stable.