search

luckycallor / InsightFace-tensorflow

Tensoflow implementation of InsightFace (ArcFace: Additive Angular Margin Loss for Deep Face Recognition).
248 stars 112 forks source link

Questions about training #23

Closed christk1 closed 5 years ago

christk1 commented 5 years ago

Hello @luckycallor and thanks for your implementation, i am trying to apply arc loss in my own dataset but loss drops from around 57 to around 20 and then it stops converging. Furthermore the training accuracy stays at 0.0. I am using a batch size of 448, any tips for this? And the other question is: for validation, if i measure the accuracy by the traditional way with tf.reduce_mean(tf.cast(tf.equal(pred, self.train_labels), tf.float32)), without comparing 2 embeddings at a time, it would be a false prediction? if yes, can you explain me the reason?

jiang7030773 commented 5 years ago

hi, @christk1, Have you solved the first problem?

christk1 commented 5 years ago

hi, @christk1, Have you solved the first problem?

hello, sorry for the late reply, after searching the official implementation on mxnet i found that you must first train with softmax and then finetune with arcloss