82 Commits (70b67f1029a8ddfa68cf2a6f0d5631b95ff591bd)

Author	SHA1	Message	Date
cc	68398abce9	[Inference] zero_copy_tensor supports int8_t (#30053) ... * zero_copy_tensor supports int8_t	5 years ago
joanna.wozna.intel	840c521b77	Fix problem with flags fp32 and int8 (#27954)	5 years ago
joanna.wozna.intel	ddcd1b5381	Add bfloat16 resnet50 test (#27755)	5 years ago
Wojciech Uss	f399bed8d9	Add an option to set number of warmup iterations (#27739)	5 years ago
Wilber	f8e370ac7f	[Inference] [unittest] Inference unit tests rely on dynamic libraries (#24743)	5 years ago
石晓伟	17ac6e2580	update the analysis predictor for multi-stream support, test=develop (#24046) ... * update the analysis predictor, test=develop * update the unit test, test=develop * no priority set before the inferface determined, test=develop * interface name generalization, test=develop	6 years ago
GaoWei8	250a192181	Add ernie large c++ inference test (#21365) ... * add ernie-large test test=develop * add ernie large c++ inference test test=develop	6 years ago
Tao Luo	01fa4ead61	fix -Wno-error=sign-compare warning in gcc8 (#21434) ... * fix -Wno-error=sign-compare warning in gcc8 test=develop * fix warning in distributed codes test=develop	6 years ago
lidanqing	c0aa13672e	Fp32 vs int8 qat C++ performance (#21244) ... * add ut for comparing FP32 and QAT INT8 * add save qat transformed model python script test=develop * updated * added missing file * add "with_label" test=develop * performance benchmark as unit test test=develop * change names of unnecessary thing * Change CMakeList.txt for model downloading and UT test=develop * change names of functions and params for more readable code test=develop * Change PADDLE_ENFORCE messages test=develop * fix indent problems test=develop * indent problems test=develop	6 years ago
Adam	d74ea0855f	Add relative error measure when (value > 1) (#21144) ... * Add relative error measure when value > 1 test=develop * Move code to CheckError function test=develop	6 years ago
pawelpiotrowicz	2c5c636514	Add two extra flags for test_analyzer_int8_image_classification to disable fp32/int8 (#19840) ... test=develop	6 years ago
Pei Yang	9cbc1eff2d	zerocopytensor support uint8, analysis config support profile, analysis predictor support GetInputTensorShape, test=develop (#19822)	6 years ago
lidanqing	9240e5325c	add local user data conversion into full_pascalvoc_test_preprocess.py (#19283) ... * add local user data conversion into full_pascalvoc_test_preprocess.py test=develop * change PADDLE_ENFORCE to PADDLE_ENFORCE_GE test=develop * change according to reviews test=develop	6 years ago
lidanqing	07a4d8f8d6	Fix mAP problem in unit test of int8 object detection test (#18946) ... * change the top1 comparison to mAP comparison test=develop * change the mobilenet-ssd tester demo data and batch_size settings test=develop	6 years ago
Tao Luo	3123d18787	remove unused AnalysisPredictor::SetMkldnnThreadID() (#18444) ... test=develop	6 years ago
翟飞跃	de42fe8fd5	Change int8v2 CAPI unit test name and add log in the prediction stage (#18200) ... * fix issue 18111;test=develop * fix timer;test=develop * refine code;test=develop	6 years ago
Wojciech Uss	ca5642c850	unify FP32 vs. INT8 comparison tests output (#18111) ... test=develop	6 years ago
Zhaolong Xing	ae576f3c68	fix: when use the load model from memory mode, the RAM occupy is high (#17788) ... test=develop	6 years ago
Zhaolong Xing	4337009b92	fix trt ci timeout error (#17701) ... test=develop	7 years ago
Wojciech Uss	984aa90583	improved unit test output (#17266) ... added printing data type to differentiate int8 and fp32 latency results test=develop	7 years ago
tensor-tang	79ed1c76cd	fix bn fuse vardesc and add model saver (#17143) ... * fix bn fuse vardesc and add model saver test=develop * unify save model in test helper test=develop * fix mkdir on windows test=develop * remove magic number use bn bias var desc test=develop	7 years ago
Tao Luo	d5c8d4acfe	reduce all analyzer_test ci elasped time ... test=develop	7 years ago
luotao1	bd636a9ea6	test_analyzer_int8 tests use default pass order ... test=develop	7 years ago
Wojciech Uss	9b6a029666	fix dataset reading and add support for full dataset (#16559)	7 years ago
Sylwester Fraczek	fe21578a44	create test for quantized resnet50 ... test=develop	7 years ago
luotao1	1283833395	zero_copy tensor support INT32 ... test=develop	7 years ago
luotao1	31c4e1d9fc	Merge branch 'develop' into zero_copy	7 years ago
luotao1	9e2c7e69fb	simplify the zero_copy tests ... test=develop	7 years ago
luotao1	aeee4cbe71	add compare between zerocopy and analysis	7 years ago
luotao1	fad06cb928	unify ZeroCopy in analysis_test	7 years ago
lidanqing	4aeb261da9	Add INT32 support. INT32 in last switch case ... test=develop	7 years ago
luotao1	06aab1b493	refine SetCpuMathLibraryNumThreads ... test=develop	7 years ago
Zhaolong Xing	90ffe74954	Merge pull request #15546 from NHZlX/fix_trt_utest_random_failed ... fix trt models utest failed.	7 years ago
Yan Chunwei	655179089f	AnalysisConfig remove contrib namespace (#15540)	7 years ago
nhzlx	95b98f27ae	fix trt models utest failed. ... test=develop	7 years ago
nhzlx	e6218c1d7b	change the input to a smaller value ... test=develop	7 years ago
nhzlx	5b92ddabe2	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_trt_stream_bug ... test=develop	7 years ago
nhzlx	2f4aee361a	fix comments ... test=develop	7 years ago
Yan Chunwei	885c4e57ab	fea/infer memory optim2 (#14953)	7 years ago
Yiqun Liu	568cc2ffa8	Optimize while_op for test (#14764) ... * Simplify the compare op for CPU. * Use asynchronous tensor copy in reshape_op's kernel. * Optimize while_op for test, avoiding creating variables every time. test=develop * Enable the cache of kernel type and kernel function. test=develop * Enable profiling with gperftools. * Remove flags for testing, and fix the linking error. test=develop * Delete the codes of ChooseKernel. test=develop * Fix bug when preparing ExecutorPrepareContext for while_op. * Fix missing depending on grpc libraries. * Remove the redundant print. test=develop * Follow comments. * Remove the codes related to prepare the ExecutorPrepareContext for while_op. test=develop	7 years ago
Tao Luo	cbd1c7c01f	fix CompareDeterministic error when test_all_data ... test=develop	7 years ago
Tao Luo	71d9097a89	fix analyzer_test runs error in native_config ... test=develop	7 years ago
Yan Chunwei	875a07c32d	refactor inference analysis api (#14634)	7 years ago
Tao Luo	85471533e0	Merge pull request #15079 from luotao1/analysis_test ... simplify analysis tests	7 years ago
Tao Luo	ecae157edf	simplify some data record in analyzer_tester ... test=develop	7 years ago
tensor-tang	d4931a2abc	support more input fake data	7 years ago
luotao1	13367866cd	add deterministic result unit-test ... test=develop	7 years ago
Tao Luo	2f55a04ec6	add refer result comparasion ... test=develop	7 years ago
Yu Yang	aa38fc4ce5	Fix compile ... test=develop	7 years ago
nhzlx	afc51e6f82	add benchmark for trt	7 years ago