144 Commits (abb49df26fe32e2cd73d1c709480f58412c810ae)

Author	SHA1	Message	Date
joanna.wozna.intel	53125c2f6f	Model converter to dot file (#23169)	5 years ago
Wojciech Uss	db052009c7	Enabled quantize all and skip missing in QAT (#24281) ... * Enabled quantize all and skip missing in QAT	5 years ago
lidanqing	61ec30f030	Update QAT INT8 2.0 doc (#24127) ... * update local data preprocess doc * update for 2.0 QAT test=develop test=document_fix * update benchmark data test=develop test=document_fix Co-authored-by: Wojciech Uss <wojciech.uss@intel.com>	5 years ago
Sylwester Fraczek	e1a7a88057	added reshape transpose matmul fuse pass (#23754)	5 years ago
arlesniak	d31a174f51	added fusing matmul-transpose-reshape pass (#23866)	5 years ago
Wojciech Uss	3d744162dd	QAT: support for new models (#23928) ... * QAT: support range-based quantization and scales from attribute * added support for channelwise	5 years ago
cc	40aa14ec77	Weight quantization support channel_wise_abs_max method to achieve higher accuracy (#23629) ... * Weight quantization support channel_wise_abs_max method to achieve higher accuracy	5 years ago
joanna.wozna.intel	12ba05ce0c	Add scale-matmul fuse pass (#23734)	5 years ago
Wojciech Uss	2383a9f7ee	[Doc update] Update for QAT INT8 MKL-DNN document (#23361) ... * Update for QAT INT8 MKL-DNN document, added info on VNNI in Windows, benchmark results added and updated	5 years ago
Wojciech Uss	1753860dd0	Enable matmul and cleanup in QAT2 (#23657)	5 years ago
cc	25628587f1	Collect output scale for quantized op and fused op (#23369) ... * Collect output scale for quantized op and fused op * Post_training_quantizaion sets batch_generator to support lod tensor	5 years ago
Bai Yifan	9bc223c8a2	fix test_graph_wrapper failure on cudnnv7, test=develop (#23451)	5 years ago
cc	3ea7c59f76	Set fuse_all_reduce_ops=false for quantization test, test=develop (#23413)	5 years ago
cc	7c55a94de5	Disable test_quantization_scale_pass unittest for random error, test=develop (#23441)	5 years ago
Yiqun Liu	bc2981e998	Disable test_code_generator and test_post_training_quantization_mobilenetv1 (#23440)	5 years ago
Wojciech Uss	9fd9067455	handle conv2d activations in older QAT models (#23202)	5 years ago
Wojciech Uss	be2ac9cc3a	separated QAT1 and QAT2 (#23284)	5 years ago
lidanqing	c524b930e7	Update QAT INT8 related code (#23104)	5 years ago
Wojciech Uss	f836c8aa8f	add check for scales and a message (#23119)	5 years ago
cc	bd80903333	Add activation_type in AddQuantDequantPass to be compatible with paddleslim, test=develop (#23221)	5 years ago
cc	589cd8782f	Post_training_quantizaion supports min_max methon (#23078) ... * Post_training_quantizaion supports min_max methon	5 years ago
lidanqing	432a4b2789	Changes QAT MKL-DNN documents (#22840)	5 years ago
cc	b6717faf80	Added an option to use external FP32 model in QAT comparison test (#22858) ... * Added an option to use external FP32 model in QAT comparison test	5 years ago
Sylwester Fraczek	5ff2439f51	fixed save qat2 model resnet50 and ernie (#22822)	5 years ago
tianshuo78520a	d2ba91aad1	fix typo words (#22653)	5 years ago
Wojciech Uss	405bb94bd1	Fix batch_num default value (#22682)	5 years ago
bingyanghuang	6abeb5c54d	fix ernie accuracy doc (#22671)	5 years ago
Wojciech Uss	fce37bc593	Doc update with Ernie QAT INT8 benchmarking (#22519) ... * Doc update with Ernie QAT INT8 benchmarking test=develop * fixes after review test=develop * remove ernie part, test=develop test=document_fix * Fix model name for qatv2 test=develop test=document_fix * Add Ernie data test=develop test=document_fix * update ERNIE benchmark with baidu QA results, test=develop test=document_fix Co-authored-by: bingyanghuang <33643817+bingyanghuang@users.noreply.github.com> Co-authored-by: Michał Gallus <sand3r@interia.eu>	5 years ago
Wojciech Uss	4cddb43c5c	Add support for Ernie NLP model to the Slim QAT (#22506) ... * a test for Ernie QAT INT8 accuracy check test=develop * Remove NLP comparison test to split PRs test=develop * Fix typo and tabs, delete commented lines test=develop * re-combine the 2 PRs, test=develop Co-authored-by: Michał Gallus <sand3r@interia.eu> Co-authored-by: bingyanghuang <33643817+bingyanghuang@users.noreply.github.com>	5 years ago
cc	d143f70a09	Post_training_quantization support set quant 8/16 bits (#22492) ... * post_training_quantization support set bits, test=develop * up, test=develop	5 years ago
cc	197913ebe1	Add weight quantization in post_training_quanzitaion (#22445) ... * support weight quantization in post_training_quanzitaion, test=develop * add test for weight quantization, test=develop	5 years ago
joanna.wozna.intel	3099d9d47c	Restore requantize squash (#22399)	5 years ago
juncaipeng	b339dff231	fix use cache file, test=develop (#22240)	5 years ago
juncaipeng	8f7372ca81	add mul and matmul quantization, test=develop (#22054) ... * add mul and matmul quantization, test=develop * add test for matmul, test=develop	6 years ago
Bai Yifan	a46bb2e6ab	Fix slim log format, test=develop (#22281)	6 years ago
lidanqing	9dff56e8e2	change qat_performance with mobilenet, change batch_size of qat2_resnet50 (#21895) ... test=develop	6 years ago
juncaipeng	8b74fc4fa7	Fix post training quantization (#21745) ... * fix post training quantization bug of memory constrained, support the input be different, test=develop	6 years ago
juncaipeng	5c4106023c	disable qat int8 test for now, test=develop (#21696)	6 years ago
juncaipeng	52f38877e4	Fix ci bug for deleting data files when other test is running (#21661) ... * fix ci bug for deleting data files, test=develop * update, test=develop	6 years ago
lidanqing	fbf9eca0d3	QAT Int8 document (#21360) ... * update benchmark for int8v2, QAT1, QAT2 accuracy and performance test=document_fix * change according to reviews test=develop test=document_fix * improve some descriptions and some models test=develop test=document_fix * update models benchmark data test=develop test=document_fix * update int8v2 and qat2 performance test=develop test=document_fix	6 years ago
juncaipeng	1f57ac1241	delete concat in AddQuantDequantPass, test=develop (#21454)	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
Liufang Sang	1840c1652c	add config file to avoid load checkpoint test=develop (#21373)	6 years ago
itminner	07e6a94268	paddleslim quantization skip pattern support list of string (#21141)	6 years ago
juncaipeng	84865b806b	add resnet50 test for post trainint quantization, test=develop (#21272)	6 years ago
Zeng Jinle	b9f8ae8494	Add global value getter setter (#21285) ... * add global value getter setter, test=develop * fix error messages, test=develop	6 years ago
juncaipeng	29b63f0aa1	support set model_filename and params_filename in post_training_quantization, test=develop (#21213) ... * support set model_filename and params_filename in post_training_quantization, test=develop	6 years ago
Liufang Sang	c91cb6c550	fix load checkpoint error in test_reader (#20924)	6 years ago
juncaipeng	00b11a4a1e	Support more ops in post training quantization, test=develop (#21073) ... * Support more ops in post training quantization, and save the output scale in quantized op. * Update docs in post training quantization and qat	6 years ago
joanna.wozna.intel	37e0e7a96b	QAT int8 accuracy little improvement (#21074) ... test=develop	6 years ago