Training from scratch issues

xiaoboCASIA / SV-X-Softmax

185 stars 20 forks source link

Training from scratch issues #5

Open davidjimenezphd opened 5 years ago

davidjimenezphd commented 5 years ago

I have reimplemented the SVX-loss function in tensorflow and I've made unit tests to verify the correct behaviour of it. However, when I train a Resnet50 architecture from scratch using SVX loss and MS1Mv2 dataset (the purged one) the loss diverges rapidly. Have you experienced something similar? Any recommendation or idea?

CloudHerods commented 4 years ago

hi, i have the same issue in mxnet!