88e9d74a75
Collecting concat output threshold, test=develop ( #24742 )
6 years ago
950892044f
fix conflict, test=develop ( #24238 )
6 years ago
6c89ca2157
Add output threshold for ops that have several output activations, test=develop ( #24726 )
6 years ago
8ef3c02e90
Update DNNL QAT document 2.0-alpha ( #24494 )
...
Update DNNL QAT document 2.0-alpha
6 years ago
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
53125c2f6f
Model converter to dot file ( #23169 )
6 years ago
db052009c7
Enabled quantize all and skip missing in QAT ( #24281 )
...
* Enabled quantize all and skip missing in QAT
6 years ago
381492fca3
add try finally, test=develop ( #24243 )
6 years ago
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>
6 years ago
e1a7a88057
added reshape transpose matmul fuse pass ( #23754 )
6 years ago
0fb9b208ab
Add batch_fc op in contrib ( #24017 )
...
* add batch fc op, test=develop
* add batch_fc_op, test=develop
* fix untest, test=develop
* rm check_dygraph, test=develop
* fix comment, test=develop
* fix comment, test=develop
6 years ago
d31a174f51
added fusing matmul-transpose-reshape pass ( #23866 )
6 years ago
3d744162dd
QAT: support for new models ( #23928 )
...
* QAT: support range-based quantization and scales from attribute
* added support for channelwise
6 years ago
6bd200db66
remove high level api ( #23854 )
6 years ago
30bd7e1c83
Add rank_attention_op attributes for GPU memory in contrib ( #23915 )
...
* optimize rank_attention, test=develop
* use the paddle memory pool, test=develop
* set max size, test=develop
* limit the max size, test=develop
* fix the head of cu, test=develop
* add AsDispensable, test=develop
6 years ago
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
f0e743f136
fix AMP and recompute ( #23551 )
...
* allow amp and recompute working together
6 years ago
12ba05ce0c
Add scale-matmul fuse pass ( #23734 )
6 years ago
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
6 years ago
8c0bdde934
Add Tdm sampler op in Contrib ( #23290 )
...
* add tdm sampler op
* fix compile bug
* fix compile bug
* fix compile bug
* fix compile bug
* test=develop, add tdm sampler unittest
* fix tdm sampler unittest
* fix input var name bug
* update tdm sampler unittest
* fix unittest
* fix unittest
* update tdm sampler unittest
* add tdm exe run unittest
* fix infershape
* test=develop, add doc
* test=develop, fix gcc8 compile bug & unittest bug
* test=develop, fix unittest
* test=develop, fix T one & zero
* test=develop, add unittest check
* test=develop, add doc smaple code & fix dype set
* test=develop, fix dtype
* test=develop, fix compile bug
* test=develop, fix unittest
* test=develop, fix unittest
* test=develop, check py3 unittest
* test=develop,fix unittest
* test=develop, fix py3&py2 unittest diff
* test=develop, fix sample code
* test=develop, fix sample code
* test=develop, fix sample code
* test=develop, fix error message
6 years ago
1753860dd0
Enable matmul and cleanup in QAT2 ( #23657 )
6 years ago
cec234b1aa
test=develop, error message of tree_conv OP enhancement ( #23574 )
6 years ago
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
9bc223c8a2
fix test_graph_wrapper failure on cudnnv7, test=develop ( #23451 )
6 years ago
c706ff20a3
fix conflict, test=develop ( #23298 )
6 years ago
a2e9af5663
Add Tdm child OP in contrib ( #23241 )
...
* add tdm child op
6 years ago
3ea7c59f76
Set fuse_all_reduce_ops=false for quantization test, test=develop ( #23413 )
6 years ago
7c55a94de5
Disable test_quantization_scale_pass unittest for random error, test=develop ( #23441 )
6 years ago
bc2981e998
Disable test_code_generator and test_post_training_quantization_mobilenetv1 ( #23440 )
6 years ago
9fd9067455
handle conv2d activations in older QAT models ( #23202 )
6 years ago
be2ac9cc3a
separated QAT1 and QAT2 ( #23284 )
6 years ago
c524b930e7
Update QAT INT8 related code ( #23104 )
6 years ago
f836c8aa8f
add check for scales and a message ( #23119 )
6 years ago
bd80903333
Add activation_type in AddQuantDequantPass to be compatible with paddleslim, test=develop ( #23221 )
6 years ago
589cd8782f
Post_training_quantizaion supports min_max methon ( #23078 )
...
* Post_training_quantizaion supports min_max methon
6 years ago
432a4b2789
Changes QAT MKL-DNN documents ( #22840 )
6 years ago
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
5ff2439f51
fixed save qat2 model resnet50 and ernie ( #22822 )
6 years ago
f05c213f98
fix basic gru lstm parameter attr bug; test=develop ( #22508 )
...
* fix basic gru lstm parameter attr bug; test=develop
* fix bias attr bug; test=develop
* add basic lstm gru name unitest; test=develop
6 years ago
433cef03e5
fix typo word ( #22784 )
6 years ago
3132681e8a
add partial_sum op in contrib ( #22292 )
...
* add partial_sum_op, test=develop
* modify the Paddle Error Message, test=develop
* modify the Paddle Error Message, test=develop
* modify the bug for python3, test=develop
* modify the ut for ci, test=develop
* mv to contrib, test=develop
* use check_variable_and_dtype, test=develop
* fix ci, test=develop
* fix conflict, test=dvelop
* add partial concat, test=develop
* fix the conflict, test=develop
* fix the error, test=develop
* rm SSE4, test=develop
6 years ago
e136661304
add partial_concat op in contrib ( #22528 )
...
* add partial_concat, test=develop
* fix the grids and blocks, test=develop
* fix the Paddle_Enforce, test=develop
* fix the doc of op, test=develop
* fix the doc, test=develop
* fix the doc of the op, test=develop
* replace -1 with None, test=develop
6 years ago
d2ba91aad1
fix typo words ( #22653 )
6 years ago
405bb94bd1
Fix batch_num default value ( #22682 )
6 years ago
6abeb5c54d
fix ernie accuracy doc ( #22671 )
6 years ago
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
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
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
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
3099d9d47c
Restore requantize squash ( #22399 )
6 years ago
b339dff231
fix use cache file, test=develop ( #22240 )
6 years ago
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
a46bb2e6ab
Fix slim log format, test=develop ( #22281 )
6 years ago
83037e55ca
named_sublayers and named_parameters ( #21868 )
...
* use snake_cased Layer name
* add named_parameters and named_sublayers api
* add include_sublayers param, add unittest
test=develop
* fix named unittests
test=develop
* fix unittest
test=develop
* add api docs
test=develop
* arg fix
test=develop
* reserve rnn_impl name_scope for static graph
test=develop
* fix load static param
test=develop
* fix load static param
test=develop
6 years ago
5e07db15e6
fix init scaling value test=develop ( #22145 )
6 years ago
418abc92f4
Update pyramid related OP ( #21372 )
...
* add special way to add distribute vars， Update Pyramid hash op
6 years ago
cee2ccb078
add shuffle batch op ( #21674 )
...
* add shuffle batch op, test=develop, test=document_preview
* fix size_t conflict and check_output test=develop, test=document_preview
* fix bug test=develop, test=document_preview
* add unittest of shuffle_batch layer test=develop, test=document_preview
* fix py coverage and op input type, test=develop, test=document_preview
* fix py coverage, test=develop
* fix en doc, test=develop
* move to contrib test=develop
* add unique_name test=develop
* invoke shuffle_batch in contrib.layers test=develop
6 years ago
9dff56e8e2
change qat_performance with mobilenet, change batch_size of qat2_resnet50 ( #21895 )
...
test=develop
6 years ago
8b74fc4fa7
Fix post training quantization ( #21745 )
...
* fix post training quantization bug of memory constrained, support the input be different, test=develop
6 years ago
f6144d8463
remove build_once & name_scope ( #21131 )
...
* remove build_once & name_scope (Conv2D)
test=develop
* fix unittest
test=develop
* Conv2DTranspose
* Conv3D & Conv3DTranspose
test=develop
* Pool2D & BatchNorm
* Embedding
* LayerNorm
* GRUUnit & NCE
* PRelu
* BilinearTensorProduct
* GroupNorm & SpectralNorm
* TreeConv
test=develop
* fix LayerNorm in transformer unnittest
test=develop
* disable LayerNorm or BatchNorm in multicard
test=develop
* refine Layer.create_parameter api
test=develop
* refine LayerNorm, remove begin_norm_axis param, add normed shape check
test=develop
* LayerNorm bug fix
test=develop
6 years ago
5c4106023c
disable qat int8 test for now, test=develop ( #21696 )
6 years ago
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
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
1f57ac1241
delete concat in AddQuantDequantPass, test=develop ( #21454 )
7 years ago
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
07e6a94268
paddleslim quantization skip pattern support list of string ( #21141 )
7 years ago
be2e3e67d9
Fix some typos in AMP. ( #21354 )
...
* fix some typos in AMP. test=develop
* delete useless codes. test=develop
7 years ago
84865b806b
add resnet50 test for post trainint quantization, test=develop ( #21272 )
7 years ago
b9f8ae8494
Add global value getter setter ( #21285 )
...
* add global value getter setter, test=develop
* fix error messages, test=develop
7 years ago
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
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
37e0e7a96b
QAT int8 accuracy little improvement ( #21074 )
...
test=develop
7 years ago
bd8b0ebaba
fix distiller typo, test=develop ( #21070 )
7 years ago
2c07727fb0
delete test resnet50 in post train quantization to avoid timeout error, test=develop ( #21081 )
7 years ago
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
175ba39c03
Add post_training_quantization ( #20800 )
...
* add post training quantization, test=develop
* specify the quantizable op type, test=develop
7 years ago
3255fe69bb
Add custom black variable name set in amp interface. ( #20875 )
...
* add custom black varname test=develop
* fix dtype test=develop
* fix num test=develop
* fix ut test=develop
* fix coverage test=develop
* fix blackvar names test=develop
7 years ago
aacd16dbb4
add pyramid_hash_op ( #20698 )
7 years ago
fd5321b3f3
modify slim print precision to round(,6), test=develop ( #20833 )
7 years ago
fa67e6e83e
Fix unitest of pruning in python3 env. ( #20825 )
...
test=develop
7 years ago
fd49ebcbd8
update int8 benchmark with 6271 data, test=develop test=document_fix ( #20736 )
7 years ago
9a3e22aad4
move nms2 to contrib, test=develop ( #20709 )
7 years ago
f201b465ec
Move pool2d to add_quant_dequant_pass, test=develop ( #20586 )
...
* move pool2d to add_quant_dequant_pass, test=develop
7 years ago
ffec9195e4
soft_label_distiller fix, test=develop ( #20645 )
7 years ago
Liufang Sang
bc4af386f4
[PaddleSlim] refine slim reader to support dataloader ( #20604 )
7 years ago
1d82025e89
Add interface so user can get scaled loss when they use customized loss. ( #20571 )
7 years ago
36acfaeeda
Add fused_embedding_seq layer into fluid.contrib ( #19771 )
7 years ago
bd99df715a
Fix basic_gru and docs of gru_unit and dynamic_gru ( #19393 )
...
* Fix docs of gru_unit and dynamic_gru.
Fix basic_gru in rnn_impl.py.
Add error messages for param_attr setting in layer_norm api.
Add int64 dtype for expand.
test=develop
* Reopen unit-tests of basic_gru/basic_lstm in rnn_impl.py.
test=develop
* Add unit test for layer_norm api.
test=develop
* Remove the deprecated gru doc fix. test=develop
* Fix basic_gru test coverage. test=develop
* Update API.spec. test=develop
* Update API.spec. test=develop
* Fix test_basic_gru coverage test. test=develop
* Update test_basic_gru in test_layers to use fluid.data
test=develop
* Update test_basic_gru for coverage. test=develop
7 years ago
a5f530a8f9
Update QAT MKL-DNN readme doc ( #20029 )
7 years ago
Liufang Sang
86c2c362ae
fix fuse_reduce_op quantization bug ( #20306 )
...
* fix fuse_reduce_op quantization bug test=develop
* close fuse_all_reduce_ops in PaddleSlim, test=develop
7 years ago
540935a825
[Bug-fix][1.6] Improve QAT accuracy ( #20174 )
...
* Leave fake quantization around mul
* Replace Fake with Real Quantized Mul
* Gather all scales from fake_quantize_ops
* Enable uint8 in conv_relu tensors
* Disable int8 mul and restore fake mul
* Fix buf for running QAT on VGG16 and 19
7 years ago
7b9e33972a
delete backward return list test=develop ( #20294 )
7 years ago
3785f08f68
fix next_tokens of controller ( #20060 )
...
* fix next_tokens of controller
7 years ago
9de6772510
Follow comment of Merged QAT PR 18970 ( #19979 )
...
* Follow Wangzhen's comment in PR 18970, test=develop
* Review comments, test=develop
* Leave fake quantization around mul
test=develop
* Replace Fake with Real Quantized Mul
test=develop
* Fix bug in quantize placement pass
Nodes in the graph now have checked type instead of node name when they are to be marked for quantization test=develop
7 years ago
28a559de12
fix PyReader._iterable usage, test=develop ( #20045 )
7 years ago
3ea2b661c0
Make PaddleSlim support PyReader ( #19995 )
...
* Make PaddleSlim support PyReader.
* Fix unittest of sensitive pruning.
* Add some assert.
7 years ago
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
766bd529d1
add optimizer:dpsgd,test=develop ( #19915 )
7 years ago
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
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
a4919d3688
move tree_conv to fluid.contrib.layers ( #19918 )
...
* move tree_conv to fluid.contrib.layers
test=develop
* update API.spec for tree_conv
test=develop
* update tree_conv api to increase unit coverage
test=develop
7 years ago
418a0967f3
move match_matrix var_conv2d et.al api into fluid.contrib test=develop ( #19859 )
7 years ago
d9db94d752
Optimize amp for multi-gpu to enable FP16 gradients transfer across gpus. ( #19714 )
...
Optimize amp for multi-gpu to enable FP16 gradients transfer across gpus
7 years ago
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
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
6c2bc29cc0
Fix float16 optimizer. ( #19682 )
...
Fix float16 optimizer
7 years ago
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
c6a598a276
init new amp, optimize inserting cast op for batchnorm ( #18596 )
...
init new amp, optimize inserting cast op for batchnorm
7 years ago
2f037c3189
fix the diff between async mode and async_half mode ( #19535 )
...
* test=develop, communicator merge add => merge average
7 years ago
1c2aae567a
Skip start epoch and end epoch when dumping strategy in PaddleSlim ( #19580 )
...
test=develop
7 years ago
abaf87be2b
Change backward_guard to optimize_guard to maximize the allreduce overlap. ( #19506 )
...
Change backward_guard to optimize_guard to maximize the allreduce overlap
7 years ago
5dce1da680
remove reset recordio usage ( #19519 )
7 years ago
ba368bf696
clean up intel labeled TODOs ( #19476 )
...
test=develop
7 years ago
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
32598ffd8f
Python infer api update and add unit test ( #19353 )
...
* python inference api supports numpy and add unit test, fix unit test fail in test_slim_int8_googlenet and test_slim_int8_mobilenet
7 years ago
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
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
2f8c7e021f
remove unused inference_transpiler unit-tests ( #19130 )
...
* remove unused inference_transpiler unit-tests
test=develop
* remove InferenceTranspiler usage in quantize_transpiler.py
test=develop
7 years ago
9150cf50fc
add save cache model api in fleet& add slots shuffle in dataset module & add metric op to calculate ctr related metrics ( #18871 )
...
* add ctr related metric layer test=develop
* add save cache and slots shuffle test=develop
* add save cache and slots shuffle test=develop
* fix error
* fix error
* fix style for ci
* fix for comments
* change SlotsShuffle input to std::strinf for generality
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix stylr
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* fix style
* change non-const reference to pointer
* fix style
* fix style
* fix style test=develop
* fix style test=develop
* add return ins num in ctr metric op
* change dtype to float in metric_op.py
* fix error test=develop
* fix style test=develop
* fix API spec
* fix API spec
* fix API spec test=develop
* add UT test=develop
7 years ago
01c7daade7
Add checking for the fetch_list of Executor.run ( #18957 )
...
* update exe.run
7 years ago
c92b78b060
Fix unitest of light nas. ( #18931 )
...
test=develop
7 years ago
d845848341
do some odd jobs ( #18641 )
...
do some odd jobs, test=develop
7 years ago
5ed713d519
remove ctr reader, all functions are satisfied in dataset ( #18672 )
...
* remove ctr reader, all functions are satisfied in dataset
7 years ago
a25be53cb5
QAT int8 MKL-DNN transformation pass with MUL ( #18322 )
7 years ago
2b4ef509ea
init custom black white list ( #18377 )
...
test=develop
7 years ago
8ed819d8e4
Call the test_slim_int8_* tests through absolute path ( #18386 )
...
test=develop
7 years ago
19da59ed3f
Remove all the code, API and doc of MKL-DNN INT8v1 ( #18347 )
7 years ago
1bdfd2eb85
Fix checkpoint of Light-NAS ( #18330 )
...
Socket can't be pickled.
test=develop
7 years ago
df2eee71d8
Sequence mask support tensor ( #18249 )
...
* sequnce mask support max length tensor input; test=develop
* add rnn_impl.py; test=develop
* add basic gru lstm unittest; test=develop
* fix api spec; test=develop
* fix sequence_mask op bug;
test=develop
test=document_preview
* change +-*x to elmentwise_op; test=develop
* add mkl flag; test=develop
* fix rnn impl bug; test=develop
* update api spec; test=develop
* fix doc bug; test=develop
* fix lstm bugs; test=develop
7 years ago
172c2facef
init black/white lists ( #17847 )
...
test=develop
7 years ago
6b3d96254d
fix some bug when merge sparse embedding parameters, test=develop ( #18223 )
...
1. fix the bug that out_put_var in SaveSelectedRows would be empty string
2. use merge_sparse_lookup_table to replace sum op for load_persistables_for_inference
3. fix the bug in _clone_var_in_block_ when the var is SELECTED_ROWS.
7 years ago
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
976cf46010
slim QAT MKL-DNN readme ( #18187 )
...
* QAT doc first version
* follow the comments, test=develop
* update the benchmark, test=develop
* Change to channel-wise, test=develop
7 years ago
5588b923f3
Add multi process reader ( #18115 )
...
* add multi process reader
test=develop
7 years ago
802ea50956
fix spelling errors ( #17941 )
...
* fix spelling errors; test=develop
* Update API.spec
update md5
* Update API.spec
* change the order of api;test=develop
7 years ago
78441c5449
add mkldnn Int8v2 slim doc ( #17909 )
7 years ago
c2fb9b906a
change dirname mobilenet to mobilenetv1 ( #18160 )
7 years ago
5cf7e7415d
update mkldnn int8v2 doc ( #18177 )
7 years ago
ca5642c850
unify FP32 vs. INT8 comparison tests output ( #18111 )
...
test=develop
7 years ago
accb132f0f
fix slim int8 mkldnn multithreading issue ( #18009 )
7 years ago
b5a1c1463d
Update CPU_NUM config ( #18059 )
...
* update CPU_NUM config
test=develop
7 years ago
78e932862c
Added unit test for QAT FP32 & INT8 comparison ( #17814 )
...
* added unit test for QAT FP32 & INT8 comparison
test=develop
* enabled other models and updated filenames
test=develop
* added accuracy check and multiple batch handling
test=develop
* removed quantization_mkldnn_pass.py
test=develop
* cleanup
test=develop
* updated model paths
test=develop
* renamed tests without MKL-DNN
test=develop
* fix reusing mkldnn pool2d primitive
test=develop
* add performance measuring
test=develop
* fix accuracy statistics
test=develop
* removed non-mkldnn tests
test=develop
* added conv2d_depthwise->conv2d mkldnn transformation
test=develop
* format update
test=develop
* fixed creating key for pool2d grad
test=develop
* added pass
* Fix the accuracy issue while using float precision to get the scale.
test=develop
* Fix the format issue when 'X' is not nchw.
test=develop
* removed output comparing and changed number of images
test=develop
* cmake and comment fix
test=develop
* updated acc threshold for QAT comparison tests
test=develop
* added OMP_NUM_THREADS setting
test=develop
* enable all QAT INT8 tests
test=develop
* restored upstream version of a file
test=develop
* modified directory names
test=develop
7 years ago
0bf2535158
Cherry-pick: fix random CI failure. ( #18011 )
...
* Cherry-pick fix random Python3 CI failure.
In some tests, SWEs used "print('xxx').format('xxx')". The syntax
is only supported in Python2, not python3. However, since those
lines are related to data download, if the CI machines already have
the data, it passes CI tests. That causes random failure.
* Cherry-pick: disable CUDNN case of test_warpctc_op
Also temporary disable a unit test. The test will be fixed under high priority.
7 years ago
96ee528e3e
fix logging basicConfig cannot be setting after import paddle ( #17786 )
...
* fix logging unable. test=develop
* unset sys.stdout for stream handler. test=develop
* fix newly add basicConfig. test=develop
* fix import error. test=develop
7 years ago
82bfa0a5ba
Enhence auto pruning and fix save/load graph when using py_reader
...
1. Enhence auto pruning.
2. Fix save/load graph when using py_reader.
test=develop
7 years ago
90ebce9ead
QAT int8 MKL-DNN transformation pass ( #17819 )
7 years ago
209a3f4e09
add log into slim mkldnn int8 test ( #17926 )
7 years ago
5df65e506d
Add Ligth-NAS for PaddleSlim ( #17679 )
...
* Add auto pruning strategy.
1. Fix compressor.
2. Enhence graph executor.
3. Add SAController
4. Add auto pruning strategy.
5. Add unitest for auto pruning strategy.
test=develop
* Init light-nas
* Add light nas.
* Some fix.
test=develop
* Fix sa controller.
test=develop
* Fix unitest of light nas.
test=develop
* Fix setup.py.in and API.spec.
test=develop
* Fix unitest.
1. Fix unitest on windows.
2. Fix package importing in tests directory.
* 1. Remove unused comments.
2. Expose eval_epoch option.
3. Remove unused function in search_agent.
4. Expose max_client_num to yaml file.
5. Move flops constraint to on_epoch_begin function
test=develop
* Fix light nas strategy.
test=develop
* Make controller server stable.
test=develop
* 1. Add try exception to compressor.
2. Remove unitest of light-nas for windows.
test=develop
* Add comments
Enhence controller
test=develop
* Fix comments.
test=develop
7 years ago
cc
ShenLiang
lidanqing
joanna.wozna.intel
Wojciech Uss
Leo Chen
Sylwester Fraczek
arlesniak
zhangchunle
mapingshuo
Chengmo
silingtong123
Bai Yifan
Yiqun Liu
hong
tianshuo78520a
ShenLiang
bingyanghuang
songyouwei
gongweibao
Chengmo
zhoushiyu
Liufang Sang
itminner
Zhen Wang
Zeng Jinle
Aurelius84
whs
wangguanzhong
翟飞跃
Guo Sheng
Michał Gallus
xiteng1988
jhjiangcs
Tao Luo
Aurelius84
Jie Fang
Bai Yifan
Chen Weihang
123malin
liu zhengxi
Jiancheng Li
yaoxuefeng
chengduo
tangwei12
guru4elephant
songhao
chengduo
Huihuang Zheng
Kaipeng Deng