out = w * input
where w is a parameter of size 1

Change-Id: Ife682d62323ceb1a20cbbf6269421b20a862d888

* set mixedlayer output size according to input operator
* change from num_channel to num_channels for conv_operator (the old one is
really misleading because all the others are num_channels)

* also changed the arg name in projections.py

* Fix lots of trainer_config_helpers bug, and complete unittest for `layers.py`