Added a test in test_NetworkCompare to verify cudnn and exconv, fixed a bug in cudnn_conv in dealing with groups

The instance weight and coeff are only mulipled to the gradient with respect to input.

Change-Id: Ic80845c892c96c37a0df0ddc433fe1aeaa5a9d1c

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

Change-Id: Ife682d62323ceb1a20cbbf6269421b20a862d888

* Check all files by pre commit hooks

rebase deconv implementation with develop branch and resolve conflicts with pull#218 commit 45c81a41

And rebase

Change-Id: I7ea234b3aa8fc70675af15d91db08242c43fb5ff

This allows user to implement any type of cost by summing over the output of non-cost layers.

Change-Id: Ic55aaabbf0c1299e70b8e48a0effcc91f8f5bd29

* Add benchmark for PaddlePaddle, tensorflow and caffe

* ConvProjection to reduce memory for goolenet

* Add unit test for ConvProjection.
1. unit test in test_LayerGrad.
2. compare the ConvPorjection and CudnnConvLayer, also compare the concat_layer+img_conv_layer and concat_layer_conv_projection.

* Reduce cudnn_conv memory and add benchmark document.
1. Use TmpMatrix as the workspace in cudnn_conv to reduce gpu memory. It reduce lots of memory.
2. Add benchmark document.
3. fix smallnet_mnist_cifar.py in paddle.

* Add job=time and refine cudnn_conv to reduce gpu memroy and speed up

* Refine cudnn_conv and shared biases operation in concat_layer and mixed_layer.

* follow comments

* follow comments

* Use unique_ptr to prevent memory leaks in CudnnConvLayer.

Compiled failed on gcc 4.6

* add maxout layer, including interface and unittest

* follow maxout comments

* auto setting channels

* fix unittest bug in test_RecurrentGradientMachine