.

Results 5 comments of .

Can I create a variable shared by forward and back propagation in customop('numpy')?

@swanderingf One of the primary reasons for the `customop` wrapper is some operations are not defined in GPU. Say, I have a function using some operations defined only in CPU....

second grad error

@lryta Do we have any follow-up on this?

[Help]How can we resume from an already saved parameters ?

@rai16 The parameters are initialized by solver.init() like https://github.com/dmlc/minpy/blob/master/examples/nn/cnn.py#L94. So, to use the saved parameters, one solution is to replace the parameters after the parameter is initialized and before the...

Possible memory leakage issue with the '-=' operator.

@chenyang-tao Sorry for the delay. Can you add the complete code snippet? like the definition of `init_params` and `grad_J`. I've made a similar example and run for many times. The...

Zero gradient for concatenate

@ZihengJiang Any follow-up on this?