The chunks of types in excluded_chunk_types will not be counted in
ChunkEvaluator. This is useful for tasks such as SRL, in which chunks of
type V (verb) will not be taken into account in evaluation.
* 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.
* support rectangle padding, stride, window and input for PoolProjection
* Follow comments.
1. Remove start
2. refine img_pool_a/b.conf for test_NetworkCompare
3. Split unit test
* Modify the test in img_layers.py
* modify RecurrentGradientMachine to support hasSubSeq sequence inlinks with the same number of sentence but different number of tokens for each sentence
Change-Id: Ic71f00a4bb346b4fa93e650dfb4b1a0d8d2338b0
dangqingqing
qiaolongfei
liaogang
Peng Li
Zhizhong Su
gaoyuan
Yu Yang
Yi Wang
Liu Yiqun
Luo Tao
qijun
Haichao-Zhang
emailweixu
zhangruiqing01
zhangjinchao01