- 13 2月, 2020 2 次提交
-
-
由 cc 提交于
Post_training_quantization support set quant 8/16 bits
-
由 Michał Gallus 提交于
* Introduce Ernie NLP * Fix error regarding incorrect attr type test=release/1.7 Co-authored-by: NWojciech Uss <wojciech.uss@intel.com>
-
- 11 2月, 2020 1 次提交
-
-
由 cc 提交于
* Add weight quantization in post_training_quanzitaion (#22445) * [cherry-pick]Support int16 for Tensor (#22423) * add int16 support, test=develop, test=release/1.7 Co-authored-by: NLeo Chen <chenqiuliang@baidu.com>
-
- 16 1月, 2020 1 次提交
-
-
由 juncaipeng 提交于
* add mul and matmul quantization, test=develop (#22054) * add test for matmul, test=develop
-
- 24 12月, 2019 1 次提交
-
-
由 lidanqing 提交于
test=develop
-
- 19 12月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* fix post training quantization bug of memory constrained, support the input be different, test=develop
-
- 12 12月, 2019 1 次提交
-
-
由 juncaipeng 提交于
-
- 11 12月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* fix ci bug for deleting data files, test=develop * update, test=develop
-
- 09 12月, 2019 1 次提交
-
-
由 lidanqing 提交于
* 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
-
- 28 11月, 2019 2 次提交
-
-
由 lidanqing 提交于
* 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
-
由 Liufang Sang 提交于
-
- 26 11月, 2019 1 次提交
-
-
由 itminner 提交于
-
- 25 11月, 2019 2 次提交
-
-
由 juncaipeng 提交于
-
由 Zeng Jinle 提交于
* add global value getter setter, test=develop * fix error messages, test=develop
-
- 20 11月, 2019 2 次提交
-
-
由 juncaipeng 提交于
* support set model_filename and params_filename in post_training_quantization, test=develop
-
由 Liufang Sang 提交于
-
- 16 11月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* Support more ops in post training quantization, and save the output scale in quantized op. * Update docs in post training quantization and qat
-
- 08 11月, 2019 1 次提交
-
-
由 juncaipeng 提交于
-
- 06 11月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* Fix bug for inserting add_quant_dequant_op to same variable repetitively in add_quant_dequant_pass, test=develop
-
- 05 11月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* add post training quantization, test=develop * specify the quantizable op type, test=develop
-
- 20 10月, 2019 1 次提交
-
-
由 bingyanghuang 提交于
-
- 16 10月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* move pool2d to add_quant_dequant_pass, test=develop
-
- 15 10月, 2019 1 次提交
-
-
由 Liufang Sang 提交于
-
- 11 10月, 2019 1 次提交
-
-
由 bingyanghuang 提交于
-
- 26 9月, 2019 1 次提交
-
-
由 whs 提交于
* Make PaddleSlim support PyReader. * Fix unittest of sensitive pruning. * Add some assert.
-
- 25 9月, 2019 1 次提交
-
-
由 Wojciech Uss 提交于
* Add support for new QAT models test=develop Co-Authored-By: NMichał Gallus <michal.gallus@intel.com> Co-Authored-By: NWojciech 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
-
- 24 9月, 2019 1 次提交
-
-
由 whs 提交于
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.
-
- 23 9月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* add fake_quant_dequant_op for average pool2d * add test
-
- 18 9月, 2019 1 次提交
-
-
由 Bai Yifan 提交于
* 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
-
- 11 9月, 2019 1 次提交
-
-
由 Bai Yifan 提交于
* split teacher checkpoints with student checkpoints, test=develop * add unittest for graph.merge(), test=develop
-
- 06 9月, 2019 1 次提交
-
-
由 Chen Weihang 提交于
* delete useless raw variables in Conv2D, test=develop * adjust the vars number in test_graph_wrapper to pass unittest, test=develop
-
- 26 8月, 2019 1 次提交
-
-
由 Leo Chen 提交于
* fix bug of getting bool Flags from os.environ, test=develop * add empty loss_name in CompiledProgram for inplace grad test, test=develop
-
- 23 8月, 2019 2 次提交
-
-
由 Jiancheng Li 提交于
* 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
-
由 Zhen Wang 提交于
* add pool2d quantization support, only for max-pooling. * add the partial quantization support.
-
- 09 7月, 2019 1 次提交
-
-
由 bingyanghuang 提交于
-
- 28 6月, 2019 1 次提交
-
-
由 Wojciech Uss 提交于
test=develop
-
- 20 6月, 2019 2 次提交
-
-
由 Wojciech Uss 提交于
* Enable MKL-DNN for slim FP32 vs. INT8 tests test=develop * added test for MobileNetV1 with MKL-DNN test=develop
-
由 bingyanghuang 提交于
* QAT doc first version * follow the comments, test=develop * update the benchmark, test=develop * Change to channel-wise, test=develop
-
- 19 6月, 2019 2 次提交