- 21 3月, 2017 2 次提交
-
-
由 wangyang59 提交于
-
由 wangyang59 提交于
-
- 27 12月, 2016 1 次提交
-
-
由 liaogang 提交于
-
- 16 12月, 2016 3 次提交
- 15 12月, 2016 1 次提交
-
-
由 xuwei06 提交于
Make sure the input size is correct. Change-Id: I2559075e32a098c5ed51942ff8351d964a6d6c75
-
- 12 12月, 2016 1 次提交
-
-
由 Yu Yang 提交于
-
- 09 12月, 2016 1 次提交
-
-
由 Yi Wang 提交于
-
- 01 12月, 2016 1 次提交
-
-
由 wangyang59 提交于
Added a test in test_NetworkCompare to verify cudnn and exconv, fixed a bug in cudnn_conv in dealing with groups
-
- 22 11月, 2016 1 次提交
-
-
由 Luo Tao 提交于
-
- 17 11月, 2016 1 次提交
-
-
由 Luo Tao 提交于
-
- 02 11月, 2016 1 次提交
-
-
由 qingqing01 提交于
* 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.
-