- 14 4月, 2021 1 次提交
-
-
由 XGZhang 提交于
-
- 08 4月, 2021 1 次提交
-
-
由 cc 提交于
* Support converting the model from fp32 to fp16
-
- 30 3月, 2021 1 次提交
-
-
由 Zhen Wang 提交于
-
- 26 3月, 2021 1 次提交
-
-
由 cc 提交于
* Use layer to calculate output scale * add backward for moving_average_abs_max_scale and save output scales to op's attr
-
- 24 3月, 2021 1 次提交
-
-
由 cc 提交于
* Refine saving output scale to infer program
-
- 21 3月, 2021 1 次提交
-
-
由 guofei 提交于
* Fix skip_quant in QAT
-
- 19 3月, 2021 1 次提交
-
-
由 cc 提交于
* Refine calculating output scale of dygraph qat, test=develop
-
- 12 3月, 2021 1 次提交
-
-
由 guofei 提交于
* Support loading parameters from checkpoint to save quantized model * Fix the unittest test_moving_average_abs_max_scale_op * Add unittest of save_quantized_model from checkpoint * Add comments to explain the function
-
- 18 1月, 2021 1 次提交
-
-
由 cc 提交于
* Collect weight threshold of lstm, test=develop
-
- 13 1月, 2021 2 次提交
-
-
由 cc 提交于
* skip quantizing ops in cpu inference, test=develop
-
由 huangxu96 提交于
* Implemented AddQuantDequantPass in imperative quantization. * Supported LeakyReLU Quantization * For meeting coverage rate. * Changed the file name of test of AddQuantDequant * Implemented more Quantized NoWeightLayers. * Fix the loss cannot align problem between static and dynamic model quantization, add swish as supported quantized layer in imperative quantization. * remove noweight_list * support 2.0 API such as Pool2D and ReLu
-
- 08 1月, 2021 1 次提交
-
-
由 guofei 提交于
* Quantization supports 2.0 APIs * Fix the error of save_quantized_model
-
- 05 1月, 2021 1 次提交
-
-
由 cc 提交于
* Avoid the scale to be infinity in quant2_int8_mkldnn_pass, test=develop * support quantized model for paddle2.0 dygraph, test=develop
-
- 30 12月, 2020 1 次提交
-
-
由 cc 提交于
* Support quantizing program_desc, test=develop
-
- 29 12月, 2020 1 次提交
-
-
由 guofei 提交于
* Fix unittest:test_imperative_skip_out
-
- 28 12月, 2020 1 次提交
-
-
由 XiaoguangHu 提交于
* rm check_import_scipy, rm chunk_eval and mean_iou in paddle.metric.__init__.py * Revert "rm check_import_scipy, rm chunk_eval and mean_iou in paddle.metric.__init__.py" This reverts commit 179ba8c2b22bc31fe8d8a126e31820792cbd0f4e. * delete paddle.metric.chunk_eval and paddle.metric.mean_iou * delete paddle.nn.clip and paddle.nn.clip_by_norm * delete paddle.nn.functional.activation.hard_sigmoid and paddle.nn.functional.activation.hard_swish * delete paddle.nn.Pool2D, paddle.nn.BilinearTensorProduct, paddle.nn.RowConv, paddle.nn.functional.row_conv * fix extension import error * fix unittest for row_conv and Pool2D
-
- 22 12月, 2020 1 次提交
-
-
由 cc 提交于
-
- 08 12月, 2020 1 次提交
-
-
由 LoveAn 提交于
-
- 30 11月, 2020 1 次提交
-
-
由 Wojciech Uss 提交于
-
- 27 11月, 2020 1 次提交
-
-
由 guofei 提交于
* Optimiz the unittest test_imperative_out_scale test=develop
-
- 25 11月, 2020 1 次提交
-
-
由 huangxu96 提交于
* Impelement 2.0 API version Conv2d and Linear layer quantization in imperative mode. * use cudnn softmax in static Lenet * Modified ChannelwiseQAT Unittest for 2.0 API. * For CI python coverage.
-
- 18 11月, 2020 1 次提交
-
-
由 Bai Yifan 提交于
* support user-defined quant and preprocess
-
- 08 11月, 2020 1 次提交
-
-
由 YUNSHEN XIE 提交于
* disable ut test_parallel_executor_fetch_isolated_var,test=document_fix * test for limiting ut exec time as 15S * fix an error caused by cannot find ut * fix some error * can not find test_transformer * fix error caused by ut not run in windows * fix error caused by Compiler Options * fix error caused by setting timeout value as 15 in python/paddle/tests/CMakeLists.txt * setting timeout value to 120s for old ut * add the timeout value setting * fix error caused by ut only run in coverage_ci * add analyzer_transformer_profile_tester * fix some error * fix some error * fix error with inference option * fix error with inference option setting as ON_INFER * add some ut to set timeout * modified some option * fix error * fix some timeout error * fix error * fix error * fix timeout for test_analyzer_bfloat16_resnet50 * fix error * setting timeout properity for some ut * first pr for new ut timeout as 15S
-
- 14 10月, 2020 1 次提交
-
-
由 guofei 提交于
* Implement the function of OueScaleForTraining/OutScaleForInference in dygraph test=develop
-
- 11 10月, 2020 1 次提交
-
-
由 Chen Weihang 提交于
* replace config by kwargs * change save path form dir to prefix * fix failed unittests * revert unittest name change * polish en docs * add more tests for coverage
-
- 01 10月, 2020 1 次提交
-
-
由 Wojciech Uss 提交于
-
- 23 9月, 2020 1 次提交
-
-
由 YUNSHEN XIE 提交于
-
- 22 9月, 2020 1 次提交
-
-
由 pangyoki 提交于
* default open dygraph mode * fix CI-Mac * fix Mac-CI other unittest file * fix CI-Py3 * fix test_communicator_geo and test_buffer_shared_memory_reuse_pass * add enable_static to fix CI-Py3 * add enable_static to fix CI-coverage * delete try except
-
- 21 9月, 2020 1 次提交
-
-
由 huangxu96 提交于
* Finished ChannelWiseQuantDequantAbsMaxOp and Passed unittests. * Finished channel-wise quantize strategy in imperative quantization. * Added Cuda code of ChannelWiseQuantDequantMaxAbsOP Add Cuda code of ChannelWiseQuantDequantMaxAbsOp * Add quant_axis for channel_wise quant. * fixed a bug in unnitests, which will not trigger axis = 1 case and cannot meet the coverage rate requirement. * Added some assert infomation and fixed some coding style mistakes.
-
- 18 9月, 2020 1 次提交
-
-
由 Zhen Wang 提交于
-
- 07 9月, 2020 1 次提交
-
-
由 Sylwester Fraczek 提交于
* fix dimensions error for mobilenetv1_KL_quant fixes AssertionError: The size of weight scales vector (1000) does not match the number of output channels (1024) in the weights tensor fc7_weights. add mul test * remove comment * add third case unit test
-
- 02 9月, 2020 1 次提交
-
-
由 YUNSHEN XIE 提交于
-
- 27 8月, 2020 1 次提交
-
-
由 chalsliu 提交于
* Add the option to execute unit tests only at night * set ut nightly label for 3 cases.
-
- 25 8月, 2020 1 次提交
-
-
由 YUNSHEN XIE 提交于
-
- 24 8月, 2020 2 次提交
-
-
由 cc 提交于
* Add mnist test for post training quantization, test=develop
-
由 YUNSHEN XIE 提交于
* find timeout unittests * setting timeout value * fix some error * fix some error * fix some error * fix no newline of end file error
-
- 19 8月, 2020 1 次提交
-
-
由 cc 提交于
* Conv2d_transpose and mul support channnelwise quantization, test=develop * Skip collecting out threshold for output tensor of which the type is not fp32 or fp64, test=develop * Fix error in test_user_defined_quantization, test=develop * Add depthwise_conv_bn_fuse, test=develop * Add conv_transpose_bn_fuse_pass for post_training_quant, test=develop
-
- 31 7月, 2020 2 次提交
-
-
由 yukavio 提交于
-
由 Bai Yifan 提交于
* Remove slim from paddle framework test=develop Co-authored-by: Nwanghaoshuang <wanghaoshuang@baidu.com>
-
- 28 7月, 2020 1 次提交
-
-
由 yukavio 提交于
* saving inference model for user defined quantization model * saving inference model for user defined quantization model * fixed ci coverage
-