mx-lsoftmax
mx-lsoftmax copied to clipboard
luoyetx
mxnet version of Large-Margin Softmax Loss for Convolutional Neural Networks.
I reimplemented in tensorflow, but find it is hard to train. It is very easy get nan value. How could to avoid this?
If the function is smooth, shouldn't it not matter whether it is k or k+1 if it is at the boundary between k and k+1?
I tried using the LSoftmax files but got the errors (can be seen below): ``` perator/lsoftmax.o src/operator/lsoftmax.cc:30:3: error: stray '\302' in program insightface/lsoftmax.cc at master · deepinsight/insightface · GitHub ^...
i don't understand why we need minus w_y_i (or x_i) in the end of the formula. silly question------
Hello, Could you help explain why we need to calculate the derivative of f respect to x (df / dx)? I am confused by x. My understanding is we only...
Not only in your ReadMe, but also in my training results. The directions of each digits in the visualization are exactly same. I think the directions should depend on the...
Hi -- I was wondering where you got the idea for the specific construction of the L-softmax. It seems like maybe you could achieve a similar goal by enforcing a...
