92 Commits (7c55a94de51b1de42bd444c0d8ab20c9eeabcb4e)

Author	SHA1	Message	Date
cc	7c55a94de5	Disable test_quantization_scale_pass unittest for random error, test=develop (#23441)	6 years ago
Yiqun Liu	bc2981e998	Disable test_code_generator and test_post_training_quantization_mobilenetv1 (#23440)	6 years ago
Wojciech Uss	9fd9067455	handle conv2d activations in older QAT models (#23202)	6 years ago
lidanqing	c524b930e7	Update QAT INT8 related code (#23104)	6 years ago
cc	589cd8782f	Post_training_quantizaion supports min_max methon (#23078) ... * Post_training_quantizaion supports min_max methon	6 years ago
lidanqing	432a4b2789	Changes QAT MKL-DNN documents (#22840)	6 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	6 years ago
Sylwester Fraczek	5ff2439f51	fixed save qat2 model resnet50 and ernie (#22822)	6 years ago
Wojciech Uss	405bb94bd1	Fix batch_num default value (#22682)	6 years ago
bingyanghuang	6abeb5c54d	fix ernie accuracy doc (#22671)	6 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>	6 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>	6 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	6 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	6 years ago
joanna.wozna.intel	3099d9d47c	Restore requantize squash (#22399)	6 years ago
juncaipeng	b339dff231	fix use cache file, test=develop (#22240)	6 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	7 years ago
lidanqing	9dff56e8e2	change qat_performance with mobilenet, change batch_size of qat2_resnet50 (#21895) ... test=develop	7 years ago
juncaipeng	8b74fc4fa7	Fix post training quantization (#21745) ... * fix post training quantization bug of memory constrained, support the input be different, test=develop	7 years ago
juncaipeng	5c4106023c	disable qat int8 test for now, test=develop (#21696)	7 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	7 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	7 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	7 years ago
Liufang Sang	1840c1652c	add config file to avoid load checkpoint test=develop (#21373)	7 years ago
itminner	07e6a94268	paddleslim quantization skip pattern support list of string (#21141)	7 years ago
juncaipeng	84865b806b	add resnet50 test for post trainint quantization, test=develop (#21272)	7 years ago
Zeng Jinle	b9f8ae8494	Add global value getter setter (#21285) ... * add global value getter setter, test=develop * fix error messages, test=develop	7 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	7 years ago
Liufang Sang	c91cb6c550	fix load checkpoint error in test_reader (#20924)	7 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	7 years ago
juncaipeng	2c07727fb0	delete test resnet50 in post train quantization to avoid timeout error, test=develop (#21081)	7 years ago
juncaipeng	fa522dffa0	Fix bug in add_quant_dequant_pass, test=develop (#21018) ... * Fix bug for inserting add_quant_dequant_op to same variable repetitively in add_quant_dequant_pass, test=develop	7 years ago
juncaipeng	175ba39c03	Add post_training_quantization (#20800) ... * add post training quantization, test=develop * specify the quantizable op type, test=develop	7 years ago
bingyanghuang	fd49ebcbd8	update int8 benchmark with 6271 data, test=develop test=document_fix (#20736)	7 years ago
juncaipeng	f201b465ec	Move pool2d to add_quant_dequant_pass, test=develop (#20586) ... * move pool2d to add_quant_dequant_pass, test=develop	7 years ago
Liufang Sang	bc4af386f4	[PaddleSlim] refine slim reader to support dataloader (#20604)	7 years ago
bingyanghuang	a5f530a8f9	Update QAT MKL-DNN readme doc (#20029)	7 years ago
whs	3ea2b661c0	Make PaddleSlim support PyReader (#19995) ... * Make PaddleSlim support PyReader. * Fix unittest of sensitive pruning. * Add some assert.	7 years ago
Wojciech Uss	4286a6270d	Add support for new QAT models (#18970) ... * Add support for new QAT models test=develop Co-Authored-By: Michał Gallus <michal.gallus@intel.com> Co-Authored-By: Wojciech Uss <wojciech.uss@intel.com> * fixed fps results test=develop * fix top5 accuracy drop problem * updated for new QAT models * skip quantizing average pooling - dirty but working * add missing pass * added missing conv+brelu fuse pass * removed a call to non-existent pass test=develop * renamed pass test=develop * Adjust finding pooling scale to newest QAT models * Remove unnecessary code from quantization_mkldnn_pass * Copy Pooling input scale to output scale in QAT * Refactor & remove unused code in QAT * Incorporate fp32 FC into QAT test=develop * Enable graph drawing with debug flag test=develop * Add tests for QATv2 * Fix paths for QATv2 models test=develop * Add option to save transformed int8 qat model test=develop * Remove redundant lines from qat mkldnn pass test=develop * Delegate disablement of avg pooling to qat test=develop * fix CI bug, test=develop * Follow Wangzhen's Review, test=develop * Update API.spec test=develop * Name False in (is_unsigned, TensorScale) tuple test=develop	7 years ago
whs	bdb3e376d0	[PaddleSlim] Enhence compressor api in PaddleSlim (#19894) ... 1. Support customize eval function instead of eval program. 2. Fix loading checkpoint in quantization strategy. 3. Support saving eval model when saving a checkpoint. 4. Fix decoder of loading context in PaddleSlim. 5. Fix restoring from the checkpoint of uniform prune strategy. 6. Support saving eval model and infer model during training. 7. Add ‘unitest’ for saving eval model, saving infer model and uniform pruning restoring from the checkpoint. 8. Fix pruning of depthwise_conv_grad op by updating the groups.	7 years ago
juncaipeng	b0ceed6fb4	add fake_quant_dequant_op for average pool2d, test=develop (#19880) ... * add fake_quant_dequant_op for average pool2d * add test	7 years ago
Bai Yifan	e2c6bada36	Support dispensable student_loss in PaddleSlim distillation (#19824) ... * support_dispensable_student_loss, test=develop * add distillation test, test=develop * fix distillation test non convergence problem, test=develop * fix test_distillation fail problem, test=develop	7 years ago
Bai Yifan	aa63d5ac6d	Make the distillation process not save teacher variables in PaddleSlim (#19633) ... * split teacher checkpoints with student checkpoints, test=develop * add unittest for graph.merge(), test=develop	7 years ago
Chen Weihang	73daa3d6c0	Code Cleanup: delete three useless raw variables in Conv2D (#19644) ... * delete useless raw variables in Conv2D, test=develop * adjust the vars number in test_graph_wrapper to pass unittest, test=develop	7 years ago
Leo Chen	6fb310ae29	Fix bug of getting bool Flags from os.environ (#19349) ... * fix bug of getting bool Flags from os.environ, test=develop * add empty loss_name in CompiledProgram for inplace grad test, test=develop	7 years ago
Jiancheng Li	1799c257ad	Update Light-NAS to support latency-aware search (#19050) ... * update light_nas_strategy: add latency constraint test=develop * update light_nas_strategy: update get_model_latency test=develop * update light_nas_strategy: add more check test=develop * update light_nas test test=develop * update light_nas test test=develop * minor update light_nas test test=develop * minor update light_nas test test=develop * update light_nas test test=develop * update _constrain_func of light_nas_strategy test=develop * update _constrain_func of light_nas_strategy test=develop * remove unused code test=develop	7 years ago
Zhen Wang	0fe72469ea	Add the max-pool2d quantization support and the partial quantization support. (#19310) ... * add pool2d quantization support, only for max-pooling. * add the partial quantization support.	7 years ago
bingyanghuang	a25be53cb5	QAT int8 MKL-DNN transformation pass with MUL (#18322)	7 years ago
Wojciech Uss	8ed819d8e4	Call the test_slim_int8_* tests through absolute path (#18386) ... test=develop	7 years ago
Wojciech Uss	36b60e240a	Enable MKL-DNN for slim FP32 vs. INT8 tests (#18214) ... * Enable MKL-DNN for slim FP32 vs. INT8 tests test=develop * added test for MobileNetV1 with MKL-DNN test=develop	7 years ago