You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

tensor-tang d941192e74 fix gcc53 on cpu vec (#13020)		7 years ago
..
detail	also move a few other dir to legacy/	7 years ago
CMakeLists.txt	add cpu vec test	7 years ago
blas.cc	Follow comments and polish code names	7 years ago
blas.h	fix bugs	7 years ago
blas_impl.cu.h	matmul support float16/double	7 years ago
blas_impl.h	fix bugs	7 years ago
concat.cc	enhance the forward of concat op	7 years ago
concat.cu	fix concat synchronization bug	7 years ago
concat.h	Handle LoD for concat & seq_softmax ops	7 years ago
concat.hip.cu	…
concat_test.cc	fix errors in concat_test	7 years ago
context_project.cc	…
context_project.cu	…
context_project.h	Clean and extract blas	7 years ago
cos_sim_functor.cc	…
cos_sim_functor.cu	…
cos_sim_functor.h	…
cpu_vec.h	fix gcc53 on cpu vec (#13020)	7 years ago
cpu_vec_test.cc	fix auc layer and add check for auc op (#12954)	7 years ago
cross_entropy.cc	Check label range in cross entropy calculation. (#10954)	7 years ago
cross_entropy.cu	Revert ""cherry picked operators changes" (#12184)" (#12747)	7 years ago
cross_entropy.h	Revert ""cherry picked operators changes" (#12184)" (#12747)	7 years ago
depthwise_conv.cu	…
depthwise_conv.h	…
fc_compute.h	refine blas gemm	7 years ago
functors.h	Feature/op fusion (#12240)	7 years ago
gru_compute.cc	Clean and extract blas	7 years ago
gru_compute.cu	Clean and extract blas	7 years ago
gru_compute.h	…
im2col.cc	complete im2col with padding==1 and speedup filter width==1	7 years ago
im2col.cu	change im2sequence for ctc batch inference (#11696)	7 years ago
im2col.h	…
im2col_cfo_cpu.h	further optimize im2col using variables	7 years ago
im2col_test.cc	complete im2col with padding==1 and speedup filter width==1	7 years ago
lstm_compute.cc	…
lstm_compute.cu	…
lstm_compute.h	…
math_function.cc	Support data type int8_t . (#12841)	7 years ago
math_function.cu	Support data type int8_t . (#12841)	7 years ago
math_function.h	operators module (#12938)	7 years ago
math_function_impl.h	add hsigmoid	7 years ago
math_function_test.cc	add gemm_warp test	7 years ago
math_function_test.cu	Clean and extract blas	7 years ago
matrix_bit_code.cc	Fix the HierarchicalSigmoidGradOpKernel and refine the codes. Now hsigmoid_op is same with V2 implementation and can pass gradient check.	7 years ago
matrix_bit_code.h	Fix the HierarchicalSigmoidGradOpKernel and refine the codes. Now hsigmoid_op is same with V2 implementation and can pass gradient check.	7 years ago
maxouting.cc	…
maxouting.cu	…
maxouting.h	…
padding.h	Add pad_constant_like_op (#12943)	7 years ago
pooling.cc	fix cpplint error (#10329)	7 years ago
pooling.cu	fix cpplint error (#10329)	7 years ago
pooling.h	fix cpplint error (#10329)	7 years ago
sampler.cc	…
sampler.h	…
selected_rows_functor.cc	…
selected_rows_functor.cu	Revert ""cherry picked operators changes" (#12184)" (#12747)	7 years ago
selected_rows_functor.h	…
selected_rows_functor_test.cc	…
selected_rows_functor_test.cu	…
sequence2batch.cc	refine seq2batch	7 years ago
sequence2batch.cu	…
sequence2batch.h	bugfix lod cpu performance (#12297)	7 years ago
sequence_padding.cc	update function	7 years ago
sequence_padding.cu	update function	7 years ago
sequence_padding.h	bug fix	7 years ago
sequence_padding_test.cc	Complete sequence_padding GPU kernel	7 years ago
sequence_pooling.cc	…
sequence_pooling.cu	…
sequence_pooling.h	…
sequence_scale.cc	…
sequence_scale.cu	…
sequence_scale.h	…
softmax.cc	…
softmax.cu	Revert ""cherry picked operators changes" (#12184)" (#12747)	7 years ago
softmax.h	…
softmax_impl.h	…
unpooling.cc	…
unpooling.cu	…
unpooling.h	…
vol2col.cc	…
vol2col.cu	…
vol2col.h	…
vol2col_test.cc	…