ZhenWang
33b4963505
unify the normal and small dam model.
7 years ago
Yan Chunwei
4b7617740e
fix container not cleared ( #14231 )
7 years ago
ZhenWang
8f2e556e65
support the small dam model. test=develop
7 years ago
nhzlx
49c28b8c52
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_params_sync_pass
...
test=develop
7 years ago
nhzlx
3c83a2f720
fix comments
7 years ago
Sang Ik Lee
24e70920db
Refactor some build settings.
...
test=develop
7 years ago
Sang Ik Lee
d6125a5eec
Include ngraph in inference demo build.
...
test=develop
7 years ago
Tao Luo
b4de023ee1
Merge pull request #14636 from Superjomn/fix/word2vec
...
fix word2vec bug
7 years ago
nhzlx
d3e140a572
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_params_sync_pass
...
test=develop
7 years ago
nhzlx
d666c8eb1d
fix benchmark
7 years ago
nhzlx
900fbb83f9
add params sync pass
7 years ago
superjomn
9c665c81ae
update
...
test=develop
7 years ago
minqiyang
a02ce58f2c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into revert_vlog
...
test=develop
7 years ago
Tao Luo
e8ef14d2a7
Merge pull request #14610 from Superjomn/revert/cache_fix
...
Revert "fix transfer cache thread_local bug (#14581 )"
7 years ago
Yiqun Liu
726f2cefe3
Fix bug of referencing a temporary variable. ( #14614 )
...
test=develop
7 years ago
peizhilin
38715e6fd0
minor fix
7 years ago
superjomn
4babc6b06c
update
...
test=develop
7 years ago
minqiyang
be04d99fe4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into revert_vlog
...
test=develop
7 years ago
minqiyang
53433d7f2e
Revert the changes of VLOG
...
test=develop
7 years ago
peizhilin
36cd18b549
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
qingqing01
39ec80def4
Remove the memory copy of feeding data in C++ inference API ( #14577 )
...
* Remove the memory copy for feeding data in C++ inference API
* Fix compling dependence
* Fix compling in ONLY_CPU mode
7 years ago
peizhilin
1afa9492af
Recover the profiler
7 years ago
Yiqun Liu
bf222f197d
Use sub scope in tensor_array_to_tensor op. ( #14524 )
...
test=develop
7 years ago
dzhwinter
840c1b29ad
test=develop ( #14562 )
...
* test=develop
remove code.
* test=develop
7 years ago
Yan Chunwei
923c8e3332
add benchmark for inference ( #14571 )
7 years ago
Tao Luo
e90afec47b
Merge pull request #14543 from luotao1/threads
...
add thread related inference api
7 years ago
Zhaolong Xing
e52d90a35e
Merge pull request #14527 from hjchen2/develop
...
Refine split TensorRT plugin
7 years ago
luotao1
116979a40a
refine api name
...
test=develop
7 years ago
luotao1
e66b4c6bff
adjust tester_helper to make multi-instance multi-thread work
...
test=develop
7 years ago
luotao1
a5c4b463c9
add SetMKLDNNThreadId api
7 years ago
luotao1
e21edb26f6
add Set/GetCPUNumThreads api
7 years ago
peizhilin
7c8c9dc9bf
fix unit test cases
7 years ago
hjchen2
1adda8e06c
Add more unit tests for split plugin
...
test=develop
7 years ago
wopeizl
d9a1f3e58e
Windows/online ( #14474 )
...
* add recordio support
* disable the openblas multi-thread on windows since no support
adjust the python script
* code style
* code style
test=develop
* add create_recordio_file_reader back
* fix code style
test=develop
* fix the gtest.cmake on windows
* fix cc_test on windows
* fix the win build
test=develop
* remove fused compile support on windows
test=develop
* add the jit support
test=develop
* add the jit support, test=develop
* add the jit support, test=develop
* add the jit back
fix compile error on windows
* rollback test=develop
* test case fix
* disable DSO by default on windows
* exclude warpctc_op on windows
* exclude the dynload_warpctc out on windows
test=develop
* fix the scripts error
test=develop
* disable avx on windows by default
test=develop
* re-organize the cmake file
* disable mkl on windows by default
* add warp_ctc back
* fix the dependency
* fix the dependency
* fix the build issue on windows
* remove unsupported flag on windows
* code style
* code style
test=develop
* fix issue
* add profiler, parallel_executor back
* clean up the pre-definitions on windows
* fix build issue
* test=develop
7 years ago
peizhilin
bef475c92b
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
hjchen2
6eba5bd276
Fix direct copy and refine split ut
...
test=develop
7 years ago
Qiao Longfei
fd290c2580
fix mac compile of analysis
...
test=develop
7 years ago
hjchen2
5857fb3014
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
...
test=develop
7 years ago
hjchen2
3e3599f3d9
Refine split tensorrt plugin
7 years ago
peizhilin
f10e196fc8
fix build issue
7 years ago
Zhaolong Xing
ad349e770f
Merge pull request #14452 from NHZlX/fix_avg_pool_trt_bug
...
fix avg pool trt bug
7 years ago
peizhilin
6e66fadb95
clean up the pre-definitions on windows
7 years ago
Tao Luo
1d9b2a453c
Merge pull request #14508 from luotao1/warm_up_multi_thread
...
add warm up in TestMultiThreadPrediction
7 years ago
nhzlx
e62872df8b
fix conflicts
7 years ago
nhzlx
a4dc1d4292
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refine_trt
...
test=develop
7 years ago
nhzlx
faeb9b8aa9
fix compile rely problem
7 years ago
Tao Luo
eb9b9becdc
add warm up in TestMultiThreadPrediction
...
test=develop
7 years ago
Tao Luo
5cc7946313
Merge pull request #14499 from luotao1/disable_openblas_test
...
disable two openblas test temporary
7 years ago
nhzlx
2a84054372
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refine_trt
...
test=develop
7 years ago
nhzlx
b742d46520
fix demo ci bug on trt
7 years ago
Houjiang Chen
33c65517fd
Update CMakeLists.txt test=develop
7 years ago
Houjiang Chen
01bda73116
Update CMakeLists.txt
7 years ago
Tao Luo
09ee266f8e
disable two openblas test temporary
...
test=develop
7 years ago
hjchen2
2c2a192eb1
Resolve merge conflicts
...
test=develop
7 years ago
Yiqun Liu
8bc1c5d2ab
Implement the Tensorrt plugin for elementwise op ( #14487 )
...
* Initialize the elementwise plugin.
* Implement the basic CUDA kernel of elementwise plugin.
test=develop
7 years ago
hjchen2
1622cb9937
Fix alpha tensor key
7 years ago
hjchen2
a8c077df7c
Implement leaky relu tensorRT converter
7 years ago
hjchen2
2825685f2a
Fix tensorrt plugin cmake dependency, test=develop
7 years ago
Superjomn
e878a8e885
update
...
test=develop
7 years ago
superjomn
4bf6817cbc
fix gpu load model
...
the parameters will load from CPUPlace, that will keep copying data
between CPU and GPU places.
test=develop
7 years ago
Wu Yi
a2d9b34417
Refine operator cmake ( #14413 )
...
* wip simplify operator framework
* wip
* wip
* done test=develop
* clean test=develop
* fix test=develop
* fix deps test=develop
* fix cpu build test=develop
* fix tensorrt build test=develop
* fix tests test=develop
* fix test=develop
* fix cpu build test=develop
7 years ago
nhzlx
8f9a8c455a
delete unused test code.
...
test=develop
7 years ago
nhzlx
83f8c403a7
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into fix_avg_pool_trt_bug
...
test=develop
7 years ago
nhzlx
b969116988
fxi avg pool trt bug and fix cpplint
7 years ago
Zhaolong Xing
2f27c048cc
Merge pull request #14440 from hjchen2/develop
...
Add PRelu tensorRT plugin and Conv2d transpose op converter
7 years ago
hjchen2
6a7b995737
Refine commit message to enable ci, test=develop
7 years ago
hjchen2
413f5948b2
Fix code style
7 years ago
hjchen2
21f33b4274
Complete PRelu plugin and Conv2d transpose op converter
7 years ago
Sylwester Fraczek
8a1eeec579
add mkldnn prop_kind phase for inference-only case to pooling and activations ( #14278 )
...
* add is_test to pooling and activations
add prop_kind support for layers activation. conv and pooling
add a pass that sets is_test to true
add transpiler version of is_test pass
test=develop
* patch test and pass
test=develop
* add pass to analyzer.h
test=develop
* add is_test attr description & pass only on mkldnn
in:
activation_op.cc
batch_norm_op.cc
conv_op.cc
dropout_op.cc
lrn_op.cc
pool_op.cc
sequence_pool_op.cc
softmax_op.cc
* fix is_test handling for activation pool and conv
* change description of is_test for all layers again
* remove GetAttr(use_mkldnn) from pass
* rename correct_mkldnn_test_phase to is_test
and remove dependency on MKLDNN
test=develop
* review fix magic number
* two if(..)s into one
* Check is_test once and pass mkldnn forward prop kind
* dereference shared_ptr with * (without get())
test=develop
* add is_test_pass back
test=develop
7 years ago
Tao Luo
9d29ebc010
Merge pull request #14306 from sfraczek/sfraczek/test-analyzer-mobilenet
...
add test_analyzer_mobilenet
7 years ago
Sylwester Fraczek
d318583eb5
rename mobilenet dir to mobilenet_depthwise_conv
...
test=develop
7 years ago
Tao Luo
1d867805b0
rollback analyzer_seq_conv1_tester
...
test=develop
7 years ago
Tao Luo
5ef123c778
Merge branch 'develop' into dam_fc
7 years ago
dzhwinter
d3aed98d86
Merge pull request #14320 from wopeizl/windows/online
...
Windows/online
7 years ago
Yiqun Liu
9e6b1c5f97
Refine tester of TensorRT engine ( #14390 )
...
* Refine the tester for MixedRTPredictor.
test=develop
* Enable the profiler in TensorRT engine.
* Support the use of combined inference model in TensorRT unittest, and print the shape of feed targets.
7 years ago
peizhilin
0ef2a37c0e
merge from develop
7 years ago
nhzlx
15bdb7ef14
delete error uploaded files
...
test=develop
7 years ago
Sylwester Fraczek
2412c27c2b
Merge branch 'develop' into sfraczek/test-analyzer-mobilenet
7 years ago
peizhilin
1a9008c420
code style fix
...
test=develop
7 years ago
Tao Luo
e0d4e04bdd
fix some compiler warning
...
test=develop
7 years ago
Tao Luo
8ea13e336a
add in_num_col_dims for fc
7 years ago
nhzlx
ddb120357c
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_trt_plugin
...
merge develop and fix conflicts
7 years ago
peizhilin
447bf7c80b
test=develop
7 years ago
peizhilin
30ddc07a7e
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Yan Chunwei
9f252e0032
Combine Inference Analysis with IR ( #13914 )
7 years ago
nhzlx
0b96268057
fix comments
...
test=develop
7 years ago
nhzlx
e5bf8616f0
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_trt_plugin
...
test=develop
7 years ago
nhzlx
d38fd6a0fc
add plugin support and offer an simple split sample
7 years ago
nhzlx
2d7134bc37
add initial code for plugin
7 years ago
nhzlx
397de907ed
merge develops
...
test=develop
7 years ago
nhzlx
d6ff006903
add serial to trt test and do not print log for unused trt logs
7 years ago
peizhilin
ef8a7db81e
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
peizhilin
ca60e1d34d
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Tao Luo
433fc7c1d4
skip mkldnn related pass when use_mkldnn=false
...
test=develop
7 years ago
peizhilin
350f1f3971
remove duplicate function definition
7 years ago
peizhilin
4b1f1a8787
fix merge issue
7 years ago
peizhilin
52f7644f53
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Qiyang Min
698698f2fa
Merge branch 'develop' into fix_vlog
7 years ago
qingqing01
abe209234f
Exhaustive search for cuDNN conv. ( #14286 )
...
* exhaustive search for cuDNN conv.
* Refine code and add unit testing.
* Fix model load in fluid/inference and unit testing in conv2d
* Follow comments.
* Fix compiling test=develop
7 years ago
Tao Luo
f1046d7e37
Merge pull request #14335 from wojtuss/wojtuss/add-graph-viz
...
added additional call to graph_viz_pass
7 years ago
Sylwester Fraczek
b5f617fa9b
make mobilenet test reuse resnet50 test
7 years ago
Sylwester Fraczek
1987d45e75
add comment for depthwise pass
7 years ago
minqiyang
87450b9ad4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_vlog
...
test=develop
7 years ago
peizhilin
4ffa92d4f0
Merge branch 'develop' into windows/build
7 years ago
Tao Luo
813e54efbd
Merge pull request #14328 from PaddlePaddle/revert-14046-windows/debug
...
Revert "cherry picked windows patches."
7 years ago
minqiyang
3db9fad764
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_vlog
...
test=develop
7 years ago
minqiyang
3da43dcae2
Because anakin do NOT use glog, so we revert anakin related change
...
test=develop
7 years ago
Tao Luo
387610aae1
Merge pull request #14325 from luotao1/fix_test_analysis_predictor
...
fix test_analysis_predictor
7 years ago
peizhilin
45125ba538
fix share library issue
7 years ago
Zhaolong Xing
ba8b5619a3
Revert "cherry picked windows patches."
7 years ago
minqiyang
fcc0452c8b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_vlog
...
test=develop
7 years ago
Tao Luo
381bea0a16
fix test_analysis_predictor
...
test=develop
7 years ago
minqiyang
0c3227a523
Change the origin VLOG level to 10 times
...
Fix code to support cpplint syntax check
test=develop
7 years ago
peizhilin
869487a2b7
Merge remote-tracking branch 'origin/develop' into windows/build
7 years ago
Wojciech Uss
7fd640b882
added additional call to graph_viz_pass
...
test=develop
7 years ago
dzhwinter
234a1d9248
Merge remote-tracking branch 'origin/develop' into windows/debug
...
test=develop
7 years ago
Sylwester Fraczek
f395075efc
rebased and stuff broke
7 years ago
Sylwester Fraczek
a60957f386
addd test_analyzer_mobilenet
7 years ago
Xin Pan
80132933b7
Merge pull request #14281 from luotao1/face
...
refine analysis_resnet50_tester
7 years ago
Tao Luo
eea36739cc
refine test_helper.h
...
test=develop
7 years ago
Tao Luo
2b791f1f63
unify analyzer_face_tester to analyzer_resnet50_tester
...
test=develop
7 years ago
Tao Luo
1ead9318d5
remove unused code in test_helper.h to pass ci
...
test=develop
7 years ago
dzhwinter
2835e04409
merge develop branch. test=develop
7 years ago
qingqing01
db8c52da5e
Revert " Exhaustive search for cuDNN conv. ( #14043 )"
...
This reverts commit ce7d9b0799
.
7 years ago
qingqing01
ce7d9b0799
Exhaustive search for cuDNN conv. ( #14043 )
...
* exhaustive search for cuDNN conv.
* Refine code and add unit testing.
* Clean code
* Fix model load in fluid/inference and unit testing in conv2d
* Follow comments.
7 years ago
Tao Luo
7a2887d212
add analyzer_face_tester
...
test=develop
7 years ago
Tao Luo
2ec65ae0db
download face_model in CMakeLists.txt
...
test=develop
7 years ago
Tao Luo
2f9a5a2e0a
add analyzer_face_tester
7 years ago
nhzlx
5700fafd0f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_googlenet_bug_with_rule
...
test=develop
7 years ago
nhzlx
86b99ac953
fix comments and fix bug
7 years ago
peizhilin
1f12ba6192
gpu support, fix build issue:
...
1. Non utf-8 characters within comments of OPs may lead to protobuf fail to parse_from_string
2. comment out some ops which not supported on windows
3. cuda libs may not be correctly linked to target on windows
7 years ago
Zhen Wang
4dbc01841d
Nlp dam ( #14248 )
...
* add dam test
* update fuse_statis
* use separated dam model.
* Revert "use separated dam model."
This reverts commit 13e775c86f909b164b7cc1d35a8a24b964ec622e.
* test=develop
* modify the cmake file about infer test, test=develop.
* remove one comment, test=develop.
7 years ago
peizhilin
71d7980f69
fix build issue 1
7 years ago
peizhilin
9d67c1fb69
cpu build support
7 years ago
dzhwinter
60f70b174d
test=develop
7 years ago
Tao Luo
d2a56f7909
Merge pull request #14159 from sfraczek/sfraczek/depthwise-conv-mkldnn-pass
...
add depthwise conv mkldnn pass
7 years ago
dzhwinter
cc02353d10
test=develop
7 years ago
dzhwinter
eb2f7ed21b
refine tests. test=develop
7 years ago
Xin Pan
08d22cf7e1
Merge pull request #14091 from panyx0718/fix2
...
add program check
7 years ago
Tao Luo
fe8f178582
fix word2vec related inference unit-tests ( #14203 )
7 years ago
dzhwinter
1ace55c8ee
merge develop branch
7 years ago
Yan Chunwei
06e508ab58
fix simple_on_word2vec random fail ( #14171 )
7 years ago
dzhwinter
316765839d
add back jit simd instructions. stage.
7 years ago
Sylwester Fraczek
4e2aaf01bc
add depthwise conv mkldnn pass
...
added depthwise conv mkldnn pass which for MKLDNN changes depthwise_conv operator to conv operator because for mkldnn this is the same api
test=develop
7 years ago
dzhwinter
bf2e4cb188
cleard. staged
7 years ago
Yan Chunwei
70ce6dcd67
fix api_impl ci error ( #14140 )
7 years ago
Xin Pan
a943134a97
fix a few more tests
...
test=develop
7 years ago
dzhwinter
ebfe5a02b3
merge develop branch
7 years ago
JiabinYang
7c45e77c41
test=develop
7 years ago
Xin Pan
aa87a989ec
Merge pull request #14119 from Superjomn/fix/api-impl-tester
...
disable some tests
7 years ago
superjomn
5f7fda0b07
disable some tests
...
test=develop
7 years ago
Tao Luo
d3534d2b14
refine warning message
...
test=develop
7 years ago
Tao Luo
79da263b11
Merge pull request #14032 from sfraczek/sfraczek/fix-test-multithreading-mkldnn
...
fix test resnet50 multi-threading on mkldnn
7 years ago
Tao Luo
4928ff32a9
fix cmake warning when ON_INFER=false
...
test=develop
7 years ago
Yan Chunwei
ee74be3a49
[1.1] Bugfix/tensorarray ( #14044 )
7 years ago
Qiyang Min
33b4920d2d
Merge pull request #14057 from velconia/continue_hash_op
...
[1.1] Add hash_op implementation
7 years ago
minqiyang
7f7af5d412
Add xxhash deps to inference demo and trainer demo
...
test=develop
7 years ago
minqiyang
fe18adfbaa
Add fluid inference support
...
test=develop
7 years ago
dzhwinter
7141debe38
add cudnn back. staged.
7 years ago
Sylwester Fraczek
2098b42584
review fixes (Teamcity fails)
...
test=develop
7 years ago
dzhwinter
09409bad4d
staged. test speed=49ms in 1080.
7 years ago
Tao Luo
8ab953e37c
auto insert infer_graph_clean_pass as the default first one
...
test=develop
7 years ago
Tao Luo
ea2bdd192d
Merge branch 'develop' into remove_unused_code
7 years ago
Sylwester Fraczek
741cb33bd9
test multithreading
7 years ago
dzhwinter
468467f391
update real incnet tester
7 years ago
Zhaolong Xing
2256fae45d
Merge pull request #13938 from NHZlX/ocr_attention_support
...
ceil pool mode support for ocr attention model.
7 years ago
dzhwinter
abe8e207c4
clean demo_ci
7 years ago
dzhwinter
597d92179b
clean demo_ci
7 years ago
Tao Luo
f7bbcfa913
remove unused code in paddle_inference_api.h
...
test=develop
7 years ago
dzhwinter
c6dcffc61a
lb. add debug output
7 years ago
nhzlx
ae8f26072d
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_demo_ci_trt
...
test=develop
7 years ago
dzhwinter
607080e888
windows static library
7 years ago
Tao Luo
316bc9bfc9
fix typo and warning in analyzer_resnet50_test
...
test=develop
7 years ago
Tao Luo
42aa1d409d
Merge pull request #13485 from tpatejko/tpatejko/capi-resnet-conv-elementwise-fusion
...
MKLDNN conv+elementwise_add fusion for residual connections in Resnet
7 years ago
Tomasz Patejko
aa35aaa1ab
MKLDNN conv + elementwise_add fusion: fixing formatting
...
test=develop
7 years ago
Tomasz Patejko
1676094697
MKLDNN conv + elementwise_add fusion: turn on residual connection pass when CAPI is used.
...
test=develop
7 years ago
tensor-tang
40f8456a4f
refine fuse pattern and attr
...
test=develop
7 years ago
tensor-tang
cbbacb2534
Merge remote-tracking branch 'ups/develop' into fea/fusion_seqconv_add
...
test=develop
7 years ago
tensor-tang
603ba5e01d
add seqconv eltadd relu pass
7 years ago
Tao Luo
da722d6d9b
Merge pull request #13858 from Sand3r-/mgallus/conv-bias-pass
...
[MKLDNN] Fuse Conv + Bias using Pass
7 years ago
Tao Luo
a4b48f70c1
Merge pull request #13997 from wojtuss/wojtuss/do-not-enable-mkldnn-twice
...
do not enable MKL-DNN twice
7 years ago
Michał Gallus
f9ca31811d
Remove use mkldnn from config in resnet50 test
...
test=develop
7 years ago
Michal Gallus
91e8fbac2f
Enable MKLDNN in Resnet50Tester
...
test=develop
7 years ago
Michal Gallus
582f59c190
Conv+Bias fuse
7 years ago
Wojciech Uss
e6f480ec44
add comment on the default first pass
7 years ago
Wojciech Uss
2cf258e381
remove redundant pass list
7 years ago
Wojciech Uss
5632019f0f
add MKL-DNN placement pass
...
This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926 )
updated to use the mkldnn-placement-pass.
test=develop
7 years ago
tensor-tang
0a9f5f1790
Merge pull request #13968 from tensor-tang/fix/jit/exp
...
Fix jit exp
7 years ago
Wojciech Uss
5083ec3a1b
do not enable MKL-DNN twice
...
After the MKL-DNN placement pass there is no need to enable MKL-DNN
in operators via executor
test=develop
7 years ago
Wojciech Uss
c3b70aece9
Add MKL-DNN placement pass ( #13958 )
...
* add MKL-DNN placement pass
This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926 )
updated to use the mkldnn-placement-pass.
test=develop
* remove redundant pass list
* add comment on the default first pass
* fix test for conv+relu mkldnn fuse
7 years ago
Wojciech Uss
4a368a4901
add ifdef guard for MKL-DNN placement pass
...
test=develop
7 years ago
Tao Luo
305034f5b3
Merge pull request #13909 from luotao1/mkldnn_test
...
refine mkldnn test in analyzer_tests
7 years ago
superjomn
b77e4f4978
update
...
test=develop
7 years ago
Tao Luo
ef09862450
fix analyzer_rnn2_test
...
test=develop
7 years ago
Tao Luo
e5b4643ad8
add profile_mkldnn test
...
test=develop
7 years ago
Tao Luo
7d680be5a3
Merge branch 'develop' into mkldnn_test
7 years ago
Tao Luo
6a4e9230ed
Merge branch 'develop' into mkldnn_test
7 years ago
Tao Luo
b819684370
add compare_mkldnn test
...
test=develop
7 years ago
nhzlx
b970c6d5d0
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_demo_ci_trt
...
test=develop
7 years ago
nhzlx
32072d31b5
fix demo ci error on manylinux
7 years ago
Tao Luo
6ea9d1b595
add analysis_predictor in vis_demo
...
test=develop
7 years ago
Tao Luo
f444a7226e
Merge branch 'develop' into clean_inference_lib
7 years ago
Tao Luo
3598500773
Merge pull request #13867 from Superjomn/clean/CreatePaddlePredictor
...
clean CreatePaddlePredictor
7 years ago
Tao Luo
41eeb771e8
Merge branch 'develop' into clean_inference_lib
7 years ago
Tao Luo
b854d959a5
update with comments
7 years ago
nhzlx
2b5edfbc37
Add ceil model pooling for trt (ocr attention)
...
test=develop
7 years ago
Tao Luo
75bb0babef
Merge branch 'develop' into mkldnn_test
7 years ago
Yan Chunwei
6809238d97
fix analysis predictor profile ( #13896 )
7 years ago
nhzlx
9d98ca0424
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_googlenet_bug_with_rule
...
test=develop
7 years ago
nhzlx
849a6874ad
fix googlenet bug with relu
7 years ago
Tao Luo
a35e7f4bae
adjust demo_ci with fluid_inference_install_dir
...
test=develop
7 years ago
tensor-tang
dcfb687584
Merge pull request #13846 from tensor-tang/fix/mkldnn
...
fix default number of threads when inference with or without MKLDNN
7 years ago
Tao Luo
bd77460182
refine mkldnn test in analyzer_tests
...
test=develop
7 years ago
dzhwinter
e41a3fcd68
fix update to develop hang problem.
7 years ago
superjomn
1cfd2b51a7
update
...
test=develop
7 years ago
dzhwinter
804dd7da04
merge conflict. both linux and windows pass.
7 years ago
dzhwinter
962061f0a3
windows fix
7 years ago
superjomn
28459592cc
update
...
test=develop
7 years ago
Zhaolong Xing
7413fa458f
Merge pull request #13838 from NHZlX/add_trt_pad_op
...
Add trt pad op converter
7 years ago
superjomn
e2bd40ca82
update
...
test=develop
7 years ago
wanghaoshuang
3ae9645084
compile in linux
7 years ago
superjomn
049fcbe125
update
...
test=develop
7 years ago
superjomn
f5c0221c17
clean CreatePaddlePredictor
...
test=develop
7 years ago
nhzlx
320c78e16f
fix commets
...
test=develop
7 years ago
nhzlx
efa5bac7ad
fix demo_ci bug in vis_demo.cc
...
test=develop
7 years ago
tensor-tang
dc5a7b906d
fix default number of threads when inference with or without MKLDNN
...
test=develop
7 years ago
nhzlx
0cb88c34be
add op converter
7 years ago
Tao Luo
9b11a17502
Revert "[MKLDNN] Pass: Fuse Conv + Bias"
7 years ago
Tao Luo
ce248a15d9
Merge pull request #13368 from Sand3r-/mgallus/conv-bias-pass
...
[MKLDNN] Pass: Fuse Conv + Bias
7 years ago
Tao Luo
16b1beb244
Merge pull request #13486 from sfraczek/sfraczek/conv-bn-fuse-pass
...
Sfraczek/conv bn fuse pass
7 years ago
Michal Gallus
40b17be4b0
Pass: Fuse Conv + Bias
...
test=develop
7 years ago
nhzlx
d347ea689a
fix comments
7 years ago
nhzlx
f3af90d121
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_dy_lib
...
test=develop
7 years ago
nhzlx
f569095084
add tensorrt api lib to paddle_fluid
7 years ago
Tao Luo
84a55155ec
revert with_fast_math to ON
...
test=develop
7 years ago
dzhwinter
a46e30aa6d
enhance isinf/isnan in tensor util, avoid copy back to cpu ( #12688 )
...
* "avoid copy back to cpu"
* "add infinity support"
* "fix ci"
* "add cpu macro"
* rerun ci; test=develop
* "fix api"
test=develop
* test=develop
* test=develop
* test=develop
* test=develop
* test=develop
7 years ago
Sylwester Fraczek
78f98294c2
conv bn fuse pass
...
review fix
review from hshen14 fix
test=develop
fix error in broadcast and code cleanup
rename bias -> eltwise and added macro to shorten code
formatting
7 years ago
Tao Luo
28889caea5
disable EIGEN_FAST_MATH and use_fast_math
...
test=develop
7 years ago
Tao Luo
d770b9bda3
Merge pull request #13663 from luotao1/resnet50_ut
...
add resnet50 inference unit-test
7 years ago
Michal Gallus
09d9d77a8f
Enable MKLDNN in Naive Executor
...
test=develop
7 years ago
Tao Luo
a89afd4c22
Merge pull request #13685 from luotao1/naive_cmake
...
update libpaddle_fluid.a/so
7 years ago
luotao1
9cbf2023ab
rollback paddle_inference_helper.h to helper.h
...
test=develop
7 years ago
Tao Luo
824a82d728
Merge pull request #13672 from luotao1/gen_fluid_library
...
reduce inference ci time
7 years ago
luotao1
d55d7e04fd
update libpaddle_fluid.so with zeroCopy
...
test=develop
7 years ago
Xin Pan
425a882165
Merge pull request #13643 from panyx0718/ir2
...
clean up channel
7 years ago
luotao1
a989a4e7c2
refine paddle_inference_helper.h
7 years ago
tensor-tang
ede4b230be
Merge pull request #13553 from jczaja/prv-fused_embedding_fc_lstm_op
...
Adding fused_embedding_fc_lstm op
7 years ago
Xin Pan
ddd60581b7
clean up channel
...
test=develop
7 years ago
Tao Luo
cfbd71c223
reduce inference ci time
...
test=develop
7 years ago
JiabinYang
358b386953
test=develop
7 years ago
Tao Luo
21ee30595b
clean some CMakeLists
...
test=develop
7 years ago
Tao Luo
b31905c54d
Merge branch 'develop' into resnet50_ut
7 years ago
Tao Luo
1dcd6ee532
add resnet50 inference UT
7 years ago
Yan Chunwei
c8744d118d
fea/infer executor and concurrency performance issue bug fix ( #13451 )
...
- add naive executor
- fix concurrency performance issue
7 years ago
Jacek Czaja
910cd415f2
- Disabled embedding_fc_lstm_fuse by defult and
...
extended test_text_classification ot use new op
7 years ago
Jacek Czaja
7ab5626dee
- Added initial pass for embedding-fc-lstm
...
- Added draft of new operator
- Added fused embedding fc lstm files
- First time embedding_fc_lstm_fuse_pass was invoked in
test_text_classification
- Added Embedding pattern
- Not crashing
- Enabled draft of embedding_fc_lstm pass (does it job)
- First working (Seqcompute only) version
- Removed diagnostic comment
- First enabling of BatchCompute
- Disabling pass for embedding with is_sparse and is_distributed
- Cosmetics
- Style
- Style
7 years ago
Yan Chunwei
9e8d372ff4
hide attention lstm fuse ( #13615 )
7 years ago
nhzlx
6c81230683
update code for config change
...
test=develop
7 years ago
nhzlx
5c57e15044
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_ut_for_trt
7 years ago
Tao Luo
f67483bf3b
add seq_conv UT ( #13517 )
...
* add multi_label UT
* rename, fix typo, add fuse_statis check
7 years ago
Tao Luo
c07b2a97a9
Merge pull request #13521 from Sand3r-/mgallus/fix-pooling-ceiled-size
...
Enable MKL-DNN in Analysis Predictor
7 years ago
Michal Gallus
f465b03ef9
Enable MKLDNN in Analysis Predictor
...
Also fix MKL-DNN pooling integration for ceil mode
7 years ago
Yan Chunwei
e426cdae32
fix inference output with lod ( #13557 )
7 years ago
Yan Chunwei
5de14c6b96
refine inference api ( #13518 )
7 years ago
dzhwinter
c66a8d2cd8
add guide ( #13332 )
...
* add guide
* "fix doc"
* Update windows_inference.md
Looks like there is a little problem in markdown format writing of head lines
7 years ago
dzhwinter
24447ec517
flags ( #13541 )
7 years ago
dzhwinter
4fd5eb2255
"refine cmake" ( #13546 )
7 years ago
dzhwinter
97636a9fcf
"fix link error" ( #13545 )
7 years ago
nhzlx
baae7e4f63
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_ut_for_trt
7 years ago
nhzlx
2763321684
fix comments
7 years ago
Yan Chunwei
90bc14da24
simple fix on inference tester helper ( #13507 )
7 years ago
nhzlx
0514882bc5
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_ut_for_trt
7 years ago
nhzlx
1f6c9dbad4
fix typo
7 years ago
nhzlx
f277f53c33
out of memory... i bet it's the last time commit for this pr
7 years ago
Tao Luo
b75887514e
Refine infer api test ( #13472 )
...
* refine analyzer_nlp_tester
* refine analyzer_rnn/vis_tester
7 years ago
nhzlx
0c51170052
fix the ut test error :)
7 years ago
nhzlx
4801beb101
add arguments for trt config
7 years ago
nhzlx
4c52be07dd
fix ut error
7 years ago
nhzlx
94a57f1d83
add trt config to arguments
7 years ago
nhzlx
68fb818aa8
add ut of trt common models
7 years ago
Tao Luo
2d89849125
add WITH_INFERENCE_API_TEST option ( #13425 )
7 years ago
nhzlx
cc4a7661c6
merge develop
7 years ago
nhzlx
d40402f9b7
add dropout and sigmoid op converter
7 years ago
Jiabin Yang
edb9e56934
Merge pull request #13401 from JiabinYang/mac/ci_unitest
...
add unitttest for mac on ci after some untest being disable
7 years ago
dzhwinter
85f8dd1c77
debug version
7 years ago
Yan Chunwei
3725f22442
Hotfix/api predictor ( #13383 )
...
* hotfix for PaddleTensor buffer.
7 years ago
Tao Luo
65b1fbb5d8
Merge pull request #13399 from luotao1/fix_cmake
...
fix text_classification download error
7 years ago
dzhwinter
e1999538eb
debug the device context
7 years ago
dzhwinter
372caf4000
windows staff
7 years ago
JiabinYang
87b11179e5
add unitttest for mac on ci after some untest being disable
7 years ago
tensor-tang
5fd2ffdce7
Merge pull request #13372 from tensor-tang/fea/ut/vis
...
add analysis vis ut
7 years ago
luotao1
e93c7b62dc
fix text_classification downlaod error
7 years ago
tensor-tang
26fc698f85
disable mkldnn fuse on ocr test
7 years ago
JiabinYang
9a9105018d
fix mac compile error in subgraph_splitter
7 years ago
tensor-tang
1a99302c14
refine and reuse code
7 years ago
tensor-tang
b7a64e8698
fix confilts
7 years ago
tensor-tang
4e4f952dea
Merge remote-tracking branch 'ups/develop' into fea/ut/vis
7 years ago
tensor-tang
89d09e6594
Merge branch 'develop' into fea/ut/vis
7 years ago
Zhaolong Xing
c9995289f1
Merge pull request #13124 from NHZlX/fix_subgraph_bug
...
Fix tensorrt subgraph bug
7 years ago
Tao Luo
d4a5326ac6
Merge pull request #13387 from luotao1/nlp_multi_thread
...
add multi-thread for nlp unit-tests
7 years ago
Tao Luo
968a56b672
Merge pull request #13373 from sfraczek/conv-relu-pass-hotfix
...
hotfix for conv-relu pass
7 years ago
tensor-tang
0bd6476f67
Merge remote-tracking branch 'ups/develop' into fea/ut/vis
7 years ago
luotao1
6b9ccd97a2
Merge branch 'develop' into nlp_multi_thread
7 years ago
luotao1
20b40cb06a
add multi-thread for nlp unit-tests
7 years ago
luotao1
29f5a93b5f
add analyzer_rnn2_test
7 years ago
nhzlx
0092ad3285
delete unused log
7 years ago
tensor-tang
dd0b2036c6
add note for use mkldnn
7 years ago
nhzlx
329a8c5283
merge develop
7 years ago
nhzlx
49bafc05bf
fix comments and set name for trt layer and ITensor
7 years ago
Sylwester Fraczek
dd149d469b
hotfix for conv-relu pass
7 years ago
tensor-tang
01f0f16884
enable mkldnn in infer api
7 years ago
tensor-tang
33c21291e7
Merge remote-tracking branch 'ups/develop' into fea/ut/vis
7 years ago
tensor-tang
65f901b36f
disable fc gru temporarily
7 years ago
tensor-tang
539b3f300f
add ocr analysis ut
7 years ago
luotao1
b12322ce95
fix fusion_lstm unique_name bug
7 years ago
Tao Luo
f351ceb65a
Merge pull request #13345 from Superjomn/bugfix/lac_test
...
fix ner_test when bs>1
7 years ago
dzhwinter
c3e1fb5a3e
add demo
7 years ago
tensor-tang
8cbb3c0720
refine lac ut and fix fetch
7 years ago
superjomn
8e0fe035d4
fix ner_test when bs>1
7 years ago
nhzlx
df161e08f0
delete unuse ut
7 years ago
nhzlx
49b5b3c5b3
merge develop
7 years ago
nhzlx
03ff4f6892
fix subgraph bug!
7 years ago
Tao Luo
94b66bdb5d
Merge pull request #13326 from luotao1/analysis_test_refine
...
refine Analysis test
7 years ago
Xin Pan
17bf8713a5
Merge pull request #12988 from panyx0718/ir2
...
program and tensor versioning support
7 years ago
luotao1
9664c53c7c
fix cmake error to pass the ci
7 years ago
luotao1
81c21705b4
simplify inference/tests/api/CMakeLists.txt
7 years ago
luotao1
d0fbe78040
move analyzer_xxx_tester to inference/tests/api
7 years ago
luotao1
83af1b3b3e
move analyzer_rnn1_test out of analyzer_test
7 years ago
Yan Chunwei
2fd1bf2ea6
fea/add color log ( #13305 )
7 years ago
Yan Chunwei
5023530a8a
Refactor/remove sensitive ( #13314 )
7 years ago
Yan Chunwei
478a4e850e
refactor ir pattern ( #13304 )
7 years ago
Xin Pan
4313d870a2
refine
7 years ago
Xin Pan
c69cf6dde8
fix
7 years ago
Xin Pan
926e1077ca
version
7 years ago
tensor-tang
ca973139fe
Merge pull request #13285 from tensor-tang/refine/ut/lac
...
add analysis unit test of lac and ner
7 years ago
tensor-tang
5a2fc5b52f
fix print error
7 years ago
tensor-tang
3ea19b7596
fix bug and fc pass ut
7 years ago
tensor-tang
acfdbf0293
enable ner analysis test and refine lac
7 years ago
tensor-tang
df0c695618
fix fusion gru pass and enable it
7 years ago
luotao1
d4c3fe9a44
clean api_anakin_engine_rnn_tester
7 years ago
tensor-tang
7eebb90523
fix conflicts
7 years ago
tensor-tang
3c3ad1e4cf
Merge branch 'develop' into refine/ut/lac
7 years ago
tensor-tang
ca30127e0a
fix compile error undef registrar pass
7 years ago
tensor-tang
0618077971
Merge remote-tracking branch 'ups/develop' into refine/ut/lac
7 years ago
tensor-tang
6b104c90d3
fix profile
7 years ago
luotao1
00c7230996
Merge branch 'develop' into all_data
7 years ago
Yan Chunwei
6de0a18d5f
Refine/text classification support data ( #13256 )
7 years ago
Tao Luo
11b22883be
Merge pull request #12738 from luotao1/anakin_cpu
...
support anakin for only-cpu environment
7 years ago
Xin Pan
883bbe1958
Merge pull request #13238 from panyx0718/clean
...
Clean
7 years ago
luotao1
4c283d87ef
Merge branch 'develop' into all_data
7 years ago