Closed tuanphan09 closed 3 years ago
Actually not. The better strategy is, in the earlier stage of the learning (0\~80k steps) using softmax pretraining or random batch learning, then (80\~110k learning steps) using hard negative mining. In report. EER for random batch strategy is 8%, EER for hard negative mining is 6%.
Thank you.
Could you tell me how did you get the 17k pretrained model in checkpoint model (with/without hard negative mining, how many steps?)? I'm trying to compare my model with yours and working on this task with GAN like this paper
You can get pretrained model in the following steps.
constant.py
, set PRE_TRAIN = False
pretraining.py
I approximately run 80,000 steps in softmax pretraining.I am not familiar with GAN, and I look forward to seeing your results on GAN.
Based on your report, training with random batch was better than using hard negative mining, right?