2. Make SwitchOrderLayer support for softmax activation
3. Fix bugs

1. Add switch function for switching image dimensions order
2. Add CpuMatrix::backwardSoftmax function
3. Add pixel softmax layer, python wrapper and grad_test

Fix #2567

Change the CpuMatrix::copyFrom and CpuVector::copyFrom with the stream parameter to the synchronous interface.

No longer need to use SubsequenceInput. The framework will detect.

This only fixes the issue for ATLAS
MKL is still another fix.