Open Woolseyyy opened 5 years ago
About the seconde question, I have found the answer. Torch.nn.CrossEntropyLoss() combines nn.LogSoftmax() and nn.NLLLoss() in one single class.
About the seconde question, I have found the answer. Torch.nn.CrossEntropyLoss() combines nn.LogSoftmax() and nn.NLLLoss() in one single class.
have you try sphereloss in metric.py?i can`t make loss decrease
About the seconde question, I have found the answer. Torch.nn.CrossEntropyLoss() combines nn.LogSoftmax() and nn.NLLLoss() in one single class.
have you try sphereloss in metric.py?i can`t make loss decrease
my training loss is not decline too, how do you resolve this problem???
I think the focal loss here is wrong.
About the seconde question, I have found the answer. Torch.nn.CrossEntropyLoss() combines nn.LogSoftmax() and nn.NLLLoss() in one single class.
So is the implementation here of ArcFace loss right?
The focal loss function seems to be differernt from the theory. The theory describes the loss as: -alpha (1-y')^gamma log(y') - (1-alpha) y'^gamma log(1-y') Besides, the arc metric also confuses me...ArcFace is modified based on softmax but there is nothing similiar to softmax in the metric code. Maybe I misunderstand the theory. I will be grateful if you point my errors out.