110 Commits (1de32f823d634154daa818697f945b294c052d3d)

Author	SHA1	Message	Date
Wojciech Uss	4fd4095d1b	Add quantization of multi_gru op and tests (#28615)	6 years ago
guofei	638402274a	Integrate ImperativeOutScale into ImperativeQuantAware. (#27956) ... * Optimiz the unittest test_imperative_out_scale test=develop	6 years ago
huangxu96	40f5453725	Quant nn2.0 (#28764) ... * 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.	6 years ago
Leo Chen	3815d7aa40	Upgrade string literals to raw string (#28989) ... * upgrade comment string to raw string * fix string in * fix string with ' ' * revert update on comments * upgrade only necessary * fix sample code checker * fix comments with '''	6 years ago
Bai Yifan	5050e761b8	Support user-defined activation/weight quantize and preprocess. (#28570) ... * support user-defined quant and preprocess	6 years ago
cc	d1e84f3e9e	Add some ops for cacluating output scale, test=develop (#28644)	6 years ago
guofei	6bbb6e7f45	Implement the function of OutScaleForTraining/OutScaleForInference in dygraph (#26601) ... * Implement the function of OueScaleForTraining/OutScaleForInference in dygraph test=develop	6 years ago
cc	8fabb1c32f	Add test attribute in channelwise_quant op, test=develop (#27742) ... * Add test attribute in channelwise_quant op, test=develop	6 years ago
Wojciech Uss	966447e338	Added support for quantization of fusion_gru (#27518)	6 years ago
huangxu96	02606d45ef	Quant op dev (#25932) ... * 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.	6 years ago
Zhen Wang	d28162b97f	Remove save_quantized_model in ImperativeQuantAware. (#27240)	6 years ago
cc	2d8281d5ad	Remove the cache in post_traning_quantization, test=develop (#26450) ... * Remove the cache in post_traning_quantization, test=develop	6 years ago
Zhen Wang	ece74c4cd4	Update the _get_fake_quant_type definition in imperative QAT. (#27222)	6 years ago
Sylwester Fraczek	eb65877ce0	fix dimensions error for mobilenetv1_KL_quant (#26776) ... * 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	6 years ago
qingqing01	f7fb4c2212	Move hapi to python/paddle root dir. (#26442) ... * Move hapi form paddle/incubate to paddle * Remove vision/datasets/utils.py and clean code * Add sample code for conll05 * Print pull path when saving model * Fix sample code after paramter_list of SGD is changed to parameters * Fix bug in wmt16 datase	6 years ago
Pei Yang	e3f8e5cf5c	trt int8 support conv2d_transpose (#26636)	6 years ago
Aurelius84	f05613683f	[Dy2stat] Support InputSpec and Return callable class instance in @declarative (#25960) ... * add InputSpec * add unittest for tensorSpec and SimpleNet	6 years ago
Pei Yang	379222c3f1	add output scale and trt op teller support for hard_swish and hard_sigmoid (#26499)	6 years ago
cc	3f816bc8b4	[Quantization] Conv2d_transpose and mul support channnelwise quantization (#25639) ... * 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	6 years ago
Pei Yang	9e9a569dae	add trt int8 support for elementwise_mul and scale (#25676)	6 years ago
Bai Yifan	2131559d08	Remove slim from paddle framework (#25666) ... * Remove slim from paddle framework test=develop Co-authored-by: wanghaoshuang <wanghaoshuang@baidu.com>	6 years ago
cc	42189be67b	[Quant] Remove the output for moving_average_abs_max_scale op (#25697) ... * Remove the output for moving_average_abs_max_scale op, test=develop	6 years ago
Chen Weihang	23d1228c4d	remove ProgramTranslator.save_inference_model (#25740) ... * remove ProgramTranslator.save_inference_model * adapt save_quantized_model * revert buffer check implemention * remove useless import function	6 years ago
yukavio	c9285a18a0	saving inference model when user define activation or weight preprocess function (#25749) ... * saving inference model for user defined quantization model * saving inference model for user defined quantization model * fixed ci coverage	6 years ago
Zhen Wang	548cdbc544	Quantization-aware training for dygraph (#24634) ... * Add the imperative quantization aware training. * This is the python part of Imperative QAT. test=develop	6 years ago
cc	5c8e79956e	Use the specificed scope in post quant, test=develop (#25384)	6 years ago
cc	22720a1535	Fix post quant save bug, test=develop (#25370)	6 years ago
Wojciech Uss	d0a921ba98	Quant2 updates and fixes (#25313)	6 years ago
cc	d8f4714bc1	[Quantization] Save output threshold by argname_index (#25272) ... * Save output threshold by argname_index, test=develop	6 years ago
Wojciech Uss	23a4f54b73	rename qat into quant (#24948) ... test=develop	6 years ago
Wojciech Uss	56fa3880e3	rename qat into quant in filenames only (#25194) ... test=develop	6 years ago
cc	8fc31d501b	Support conv2d_traspose quantize, test=develop (#25084)	6 years ago
Liufang Sang	b174b99764	support user defined quantization func and preprocess (#24720) ... * add user defined func test=develop * update test=develop * update test=develop * fix name conflicts test=develop * add unittest test=develop * change 2018 to 2020 test=develop * add comment test=develop * add comment for function test=develop * fix details test=develop * fix details test=develop	6 years ago
cc	75eec3d1f6	Post training quantization supports optimize model by fusing (#24822) ... * Post_training_quantization supports optimize model by fusing, test=develop	6 years ago
Wojciech Uss	78d4f0cc91	add option to exclude ops by id from quantization (#24689)	6 years ago
cc	dbcd7c69e9	Update sigmoid output from Y to out, test=develop (#24765)	6 years ago
cc	88e9d74a75	Collecting concat output threshold, test=develop (#24742)	6 years ago
cc	6c89ca2157	Add output threshold for ops that have several output activations, test=develop (#24726)	6 years ago
cc	4d35112255	[Fix bug] Init scale node in OutScaleForTrainingPass and enable test_quantization_scale_pass UT (#24393) ... * Init scale node in OutScaleForTrainingPass, test=develop * Enable test_quantization_scale, test=develop	6 years ago
Wojciech Uss	db052009c7	Enabled quantize all and skip missing in QAT (#24281) ... * Enabled quantize all and skip missing in QAT	6 years ago
Sylwester Fraczek	e1a7a88057	added reshape transpose matmul fuse pass (#23754)	6 years ago
arlesniak	d31a174f51	added fusing matmul-transpose-reshape pass (#23866)	6 years ago
Wojciech Uss	3d744162dd	QAT: support for new models (#23928) ... * QAT: support range-based quantization and scales from attribute * added support for channelwise	6 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	6 years ago
joanna.wozna.intel	12ba05ce0c	Add scale-matmul fuse pass (#23734)	6 years ago
Wojciech Uss	1753860dd0	Enable matmul and cleanup in QAT2 (#23657)	6 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	6 years ago
Wojciech Uss	9fd9067455	handle conv2d activations in older QAT models (#23202)	6 years ago
Wojciech Uss	be2ac9cc3a	separated QAT1 and QAT2 (#23284)	6 years ago
Wojciech Uss	f836c8aa8f	add check for scales and a message (#23119)	6 years ago