10 Commits (bbe8f7bdcdb03778249f50a85b4162dd6a63b5bd)

Author	SHA1	Message	Date
liym27	17a6b50fe3	support num_flatten_dims=-1 of API fc. (#22634) ... * support num_flatten_dims=-1 of API fc. test=develop * fix name of class Test* and add CUDAPlace test. test=develop	5 years ago
Zhang Ting	b1da35261b	fix unit tests that do not need to inherit OpTest (#21460) ... * fix PythonAPI test in Op unittest, test=develop * fix unit tests that do not need to inherit OpTest, test=develop	6 years ago
GaoWei8	234060f88f	Add fc padding to improve mkl GEMM's performance when N and K are multiple of 128. (#20972) ... * Add fc padding to solve mkl performance test=develop * fix gpu pass and error information test=develop * fix fc_fuse_pass_test test=develop * fix error information test=develop * fix error information test=develop * fix name and add fc op padding test test=develop * fix attributes test=develop * optimize fc padding test=develop * fix test test=develop	6 years ago
Aurelius84	2213ae6bf9	Fix fp16 in input.dtype check in layers.fc (#20467) ... * Add fp16 in input.dtype check test=develop * Add warning of fp16 in CPU test=develop * add unittest code for fp16 test=develop * fix float16 list error test=develop	6 years ago
Aurelius84	729f5846cc	enhance shape error message of fc API (#20172) ... * add api check in fc test=develop * enforce shape error info of sum op test=develop * fix spelling test=develop * print x_dims info test=develop * enhance shape error info test=develop	6 years ago
Yiqun Liu	a65c728e5d	Implement the GPU kernel of fc operator (#19687) ... * Refine the codes related to fc op. * Add GPU implementation for fc functor. * Apply fc_fuse_pass in GPU inference. test=develop * Change the cmake for fc op. * Change PADDLE_ENFORCE to PADDLE_ENFORCE_EQ. * Add an attribute to set the activation type in fc_op. * Enhance the unittest of fc_op. test=develop * Remove the declaration of FCOpGrad back to the header file. test=develop * Set default value for newly added arguments in test_fc_op. test=develop	6 years ago
tensor-tang	f3cd2612ae	refine fc and use the fc compute in fusion_lstm	7 years ago
tensor-tang	45d0259a67	add fc forward test	7 years ago
mozga-intel	5e13314dc1	Commit	7 years ago
mozga-intel	2811ea4440	Implementation of MKLDNN FC	7 years ago