- 08 9月, 2020 1 次提交
-
-
由 wangguanzhong 提交于
* enhance collect_op for dygraph, test=develop * enhance detection ops with lod, test=develop * support none bbox left in generate_proposals, test=develop * unfiy MultiLevelRoisNum, test=develop * update core.ops, test=develop * add op register for new input & output, test=develop
-
- 11 7月, 2020 1 次提交
-
-
由 Chen Weihang 提交于
* fix softmax_with_cross_entropy cuda kernel overflow bug, test=develop * replace old macro & for condition, test=develop * polish details, test=develop
-
- 12 5月, 2020 1 次提交
-
-
由 wangguanzhong 提交于
-
- 11 5月, 2020 1 次提交
-
-
由 Chen Weihang 提交于
* add new macro BOOST_GET_SAFELY & unittests, test=develop * add different macro type, test=develop * fix get macro type in executor, test=develop * four macro part change backup * using one macro for all case, test=develop * revert attribute change, test=develop * change to three func to solve gcc4.8 bug, test=develop * polish some details, test=develop
-
- 11 4月, 2020 1 次提交
-
-
由 FDInSky 提交于
* test=develop modify some op for dyg rcnn
-
- 10 4月, 2020 1 次提交
-
-
由 wangguanzhong 提交于
-
- 10 10月, 2019 1 次提交
-
-
由 wangguanzhong 提交于
-
- 11 9月, 2019 1 次提交
-
-
由 Huihuang Zheng 提交于
TemporaryAllocator is a singleton used for allocating memory for Cudnn. Since it is a singleton, we can delete it for better performance in memory. We replace TemporaryAllocator by CUDADeviceContextAllocator and CUDADeviceContextAllocation, which uses stream callback to delete the memory allocated for the stream to avoid singleton. Also added data_feed_proto to operator to fix CI in CPU compilation
-
- 23 1月, 2019 1 次提交
-
-
由 qingqing01 提交于
* Add generate_mask_labels_op to support Mask-RCNN. * Refine sigmoid_cross_entropy to support nomalize mode. * Fix generator_proposals_label. * Use DeviceTemporaryAllocator in roi_pool and roi_algin. * Remove shape check in data_feeder.
-
- 18 10月, 2018 1 次提交
-
-
由 jerrywgz 提交于
-
- 16 10月, 2018 2 次提交
- 15 8月, 2018 1 次提交
-
-
由 Bai Yifan 提交于
Add flatten op interface and enhance APIs about detection to support variable-length image. (#12422) * add flatten api&enhance detection api * unify shape_op data type * update API.spec
-
- 01 6月, 2018 1 次提交
-
-
由 whs 提交于
* Add shape op to get the shape of variable. * Rename get_shape to shape. * Add checker for output and fix comments.
-
- 12 2月, 2018 1 次提交
-
-
由 qingqing01 提交于
-
- 10 2月, 2018 2 次提交
- 22 12月, 2017 1 次提交
-
-
由 QI JUN 提交于
* add data layout * fix ci
-
- 12 12月, 2017 1 次提交
-
-
由 QI JUN 提交于
There are mainly following fixes: - take `DeviceContext` as the template parameter of math functors and OpKernel instead of `Place` - remove `eigen_device` interface in base class `DeviceContext` - remove `GetEigenDevice` interface in `ExecutionContext` and base class `DeviceContext` - remove unused `platform::EigenDeviceConverter` - rename `REGISTER_OP_GPU_KERNEL` to `REGISTER_OP_CUDA_KERNEL` - rename `USE_GPU_ONLY_OP` to `USE_CUDA_ONLY_OP`
-
- 25 10月, 2017 1 次提交
-
-
由 Qiao Longfei 提交于
* init batch norm op * prepare input output * compute mean_out var_out save_mean save_var on CPU * active is test * use eigen to do computation * complete batch norm forward * set default momentum to 0.9 * add batch norm grad op in CPU * add tensor_format and NHWC support, add python test * add test training * add batch norm gradient test * improve comment, fix foward Python UnitTest * add gradient test * fix eigen warning * follow name style * fix a bug * change float to T * add simple forward test * test with different place * add backward test * refine python test * remove old python test code * code clean * follow code style * update comment
-
- 10 10月, 2017 1 次提交
-
-
由 Abhinav Arora 提交于
-
- 28 9月, 2017 1 次提交
-
-
由 Yu Yang 提交于
-
- 20 9月, 2017 1 次提交
-
-
由 dangqingqing 提交于
-
- 23 8月, 2017 1 次提交
-
-
由 dangqingqing 提交于
-
- 11 8月, 2017 1 次提交
-
-
由 Yu Yang 提交于
-
- 08 8月, 2017 1 次提交
-
-
由 fengjiayi 提交于
-
- 07 8月, 2017 1 次提交
-
-
由 dongzhihong 提交于
-
- 05 8月, 2017 1 次提交
-
-
由 Yi Wang 提交于
-
- 02 8月, 2017 1 次提交
-
-
由 fengjiayi 提交于
-
- 01 8月, 2017 1 次提交
-
-
由 Yu Yang 提交于
-
- 26 7月, 2017 1 次提交
-
-
由 fengjiayi 提交于
-
- 25 7月, 2017 1 次提交
-
-
由 Yu Yang 提交于
Make implement an operator less noisy.
-
- 19 7月, 2017 2 次提交
- 17 7月, 2017 3 次提交
-
-
由 qijun 提交于
-
由 Yan Chunwei 提交于
* add inputs * add ut for multiple inputs * fix AddToLayer * op_desc -> op_proto * CreateArgumentOffsetMap -> CreateInOutOffsetMap * move CreateInOutOffsetMap from OperatorBase to op registry * arg_idxs_ -> in_out_idxs_
-
由 qijun 提交于
-
- 14 7月, 2017 1 次提交
-
-
由 qijun 提交于
-
- 13 7月, 2017 2 次提交
-
-
由 Yu Yang 提交于
* Convert `op` --> `operators` * Remove AddType in OpProtoMaker, because type is part of registry. * Rename CPU_OR_GPU --> DEVICE_TYPE in registry macro.
-
由 Yu Yang 提交于
* Refine register methods, make Op can get rid of whole-archieve * `USE_OP` before a op is used. * Add unittest for add_op.
-