20 Commits (a32d420043e50d3bcc8564d768584a9b1f40b5af)

Author	SHA1	Message	Date
Yan Chunwei	3a5d6e5e64	move passes to src to avoid different behavior in deployment (#15705)	6 years ago
Yan Chunwei	897789b16e	fix save_inferece_model bug (#15365)	6 years ago
nhzlx	9641324995	fix comments ... test=develop	6 years ago
Yan Chunwei	885c4e57ab	fea/infer memory optim2 (#14953)	6 years ago
tensor-tang	a5d2a6d1ad	add fuse pass of sequared mat sub fusion	6 years ago
tensor-tang	a89296ac1f	add repeated fc relu pass	6 years ago
Zhaolong Xing	98e85f3735	add_transpose_flatten_concat_fuse (#15121)	6 years ago
tensor-tang	72d2a1801e	add seqpool concat fuse pass ... test=develop	6 years ago
Yan Chunwei	d09d6eadc0	make inference api work with Doxygen (#15195)	6 years ago
Yan Chunwei	875a07c32d	refactor inference analysis api (#14634)	6 years ago
nhzlx	02e17396c2	fix comments ... test=develop	6 years ago
nhzlx	ce3782c193	add affine_channel fuse. ... fix conv+elemenwise fuse bug.	6 years ago
nhzlx	4e4a777243	add conv+elementwiseadd pass ... test=develop	6 years ago
Yan Chunwei	a985949be9	Fea/fuse conv elementwise add fuse (#14669)	6 years ago
Yihua Xu	64e261c6cd	Implement the fusion of convolution and bias for mkldnn ... (test=develop)	6 years ago
nhzlx	900fbb83f9	add params sync pass	6 years ago
nhzlx	b742d46520	fix demo ci bug on trt	6 years ago
Sylwester Fraczek	8a1eeec579	add mkldnn prop_kind phase for inference-only case to pooling and activations (#14278) ... * add is_test to pooling and activations add prop_kind support for layers activation. conv and pooling add a pass that sets is_test to true add transpiler version of is_test pass test=develop * patch test and pass test=develop * add pass to analyzer.h test=develop * add is_test attr description & pass only on mkldnn in: activation_op.cc batch_norm_op.cc conv_op.cc dropout_op.cc lrn_op.cc pool_op.cc sequence_pool_op.cc softmax_op.cc * fix is_test handling for activation pool and conv * change description of is_test for all layers again * remove GetAttr(use_mkldnn) from pass * rename correct_mkldnn_test_phase to is_test and remove dependency on MKLDNN test=develop * review fix magic number * two if(..)s into one * Check is_test once and pass mkldnn forward prop kind * dereference shared_ptr with * (without get()) test=develop * add is_test_pass back test=develop	6 years ago
Yiqun Liu	9e6b1c5f97	Refine tester of TensorRT engine (#14390) ... * Refine the tester for MixedRTPredictor. test=develop * Enable the profiler in TensorRT engine. * Support the use of combined inference model in TensorRT unittest, and print the shape of feed targets.	6 years ago
Yan Chunwei	9f252e0032	Combine Inference Analysis with IR (#13914)	6 years ago