- 12 10月, 2017 3 次提交
-
-
由 fengjiayi 提交于
-
由 Abhinav Arora 提交于
* Adding thresholded_relu op * Adding test for thresholded relu op
-
由 QI JUN 提交于
* init * unify CopyFrom interface * fix gpu build error * fix bug in tensor_py.h * refine code comments and add TODO list * fix conflicts in FeedOp and FetchOp
-
- 11 10月, 2017 18 次提交
-
-
由 Yancey1989 提交于
-
由 Yancey1989 提交于
-
由 Yibing Liu 提交于
-
由 Yibing Liu 提交于
-
由 chengduoZH 提交于
-
由 Yancey1989 提交于
-
由 kexinzhao 提交于
* implementing softplus * small fix * small fix * small fix * small fix
-
由 chengduoZH 提交于
-
由 kavyasrinet 提交于
* Implemented the hardShrink activation * Fixing the unit test
-
由 chengduoZH 提交于
-
由 chengduoZH 提交于
-
由 chengduoZH 提交于
-
由 Siddharth Goyal 提交于
* Add numerically-stable logsigmoid activation * Add softshrink operator * Adjust relative tolerance for grad-check * Address review comments
-
由 Yan Chunwei 提交于
-
由 qijun 提交于
-
由 Yang Yang 提交于
-
由 Markus Kliegl 提交于
* conv_shift_op: initial implementation using Eigen Limitations: - both gradient outputs must be specified and are always computed - explicit for loops => could be optimized in various ways (e.g., different memory layout) * conv shift - gradient fixes fix case when not all output gradients desired * conv shift: minor cleanup * conv shift - more minor cleanup * conv shift: clean up & initial GPU implementation * fix rebase issue
-
由 qijun 提交于
-
- 10 10月, 2017 18 次提交
-
-
由 chengduoZH 提交于
-
由 chengduoZH 提交于
Separate the declarations and implementation of the PoolOp and PoolMaker class in order to reuse in pool_cudnn
-
由 chengduoZH 提交于
-
由 chengduoZH 提交于
-
由 qijun 提交于
-
由 chengduoZH 提交于
-
由 Yancey1989 提交于
-
由 Yancey1989 提交于
-
由 Yancey1989 提交于
-
由 qijun 提交于
-
由 chengduoZH 提交于
-
由 Yang Yang 提交于
-
由 Abhinav Arora 提交于
-
由 Yang Yang 提交于
-
由 Yu Yang 提交于
It will significantly reduce binary size. It is useful for mobile deployment.
-
由 Yu Yang 提交于
-
由 Abhinav Arora 提交于
* Implementing the Adamax optimizer step operator * Adding unit tests for adamax_op * Changing learning rate and time step to inputs from attributes * Changing learning rate and time step to input(tensors) * Making the Adamax operator conform to naming convention * Removing Tensor<float> from comments * Rectifying the Adamax implementation * Changing Unit Test values and adding comments * Changing Unit Test to test multiple steps
-
由 kavyasrinet 提交于
-
- 09 10月, 2017 1 次提交
-
-
由 Luo Tao 提交于
-