dengkaipeng
|
c1a69e3ea0
|
refine doc. test=develop
|
6 years ago |
|
dengkaipeng
|
65d375a09f
|
fix format. test=develop
|
6 years ago |
|
dengkaipeng
|
82d514345c
|
fix spectral_norm doc. test=develop
|
6 years ago |
|
dengkaipeng
|
24fa74d901
|
refine test_spectral_norm. test=develop
|
6 years ago |
|
dengkaipeng
|
2ea5843cbf
|
add doc and test_layers. test=develop
|
6 years ago |
|
dengkaipeng
|
037855f42d
|
fix attr dim calc. test=develop
|
6 years ago |
|
dengkaipeng
|
70dbd59839
|
add grad kernel for spectral_norm. test=develop
|
6 years ago |
|
dengkaipeng
|
72509ec3bd
|
add unittest for spectral_norm. test=develop
|
6 years ago |
|
dengkaipeng
|
3bf1ae9b59
|
add spectral_norm forwarn kenel
|
6 years ago |
|
Kaipeng Deng
|
cccde65b1c
|
Merge pull request #16043 from sneaxiy/fix_doc_md5
Fix doc md5
|
6 years ago |
sneaxiy
|
f0634da4b5
|
test=develop
|
6 years ago |
chengduo
|
e2da3a5b22
|
Revert "Add Event for TensorCopy" (#16022)
* Revert "Add Event for TensorCopy (#15953)"
This reverts commit 7235fd662b.
test=develop
* fix CI
test=develop
|
6 years ago |
Zeng Jinle
|
cae6614c98
|
Merge pull request #16005 from sneaxiy/develop-fix-executor-doc
Fix develop Executor doc
|
6 years ago |
lidanqing
|
dd1c7ee604
|
UT for conv2d_mkldnn_op with fuse_bias and fuse_residual (#16016)
test=develop
|
6 years ago |
baojun
|
9aaea38c0a
|
fix cpplint test=develop (#16028)
|
6 years ago |
tianshuo78520a
|
c6f94dd65c
|
Diff api (#16024)
|
6 years ago |
|
tianshuo78520a
|
26e3842d40
|
Update detection API add new check document (#15848)
* Update detection API add new check document
* update API.spec
* test=develop;add shanyi15 approved API.spec
* test=develop;update PM check API.spec
* check api.spec
* test=develop
* update API.spec
* test=develop;update API.spec
* update API.spec
* cat API.spec
* update documnent in api.spec
* check python35 api.spec
* update print_signatures md5 function
* test=develop
* update API.spec
* test=develop;fix python3 API.spec diff
* test=develop
* test=develop
* test=develop
|
6 years ago |
Tao Luo
|
96f7fc60ee
|
Merge pull request #16013 from kbinias/kbinias/poll-mkldnn-ut
MKL-DNN: Add a unit test for pooling when ceil mode is enabled
|
6 years ago |
|
chengduo
|
ae37f82964
|
Unified ParallelExecutor and Compiler (#15970)
* Unified ParallelExecutor and Compiler
|
6 years ago |
Krzysztof Binias
|
54f21a5c47
|
Add test for ceil mode
test=develop
|
6 years ago |
|
chengduo
|
7235fd662b
|
Add Event for TensorCopy (#15953)
Add Event for TensorCopy
|
6 years ago |
|
sneaxiy
|
7c4303bc4a
|
Fix doc
test=develop
|
6 years ago |
Zhen Wang
|
46c5e37858
|
improve save_persistable api doc. test=develop (#15911)
|
6 years ago |
Tink_Y
|
31d830de9f
|
refine image_resize annotation (#15976)
* fix image_resize annotation
test=develop
* fix some typo
* Update nn.py
* Update interpolate_op.cc
test=develop
|
6 years ago |
tangwei12
|
6d5a04c1e7
|
add op type in check nan/inf (#15986)
* add op name in check nan/inf, test=develop
|
6 years ago |
Qiyang Min
|
187cffd019
|
Merge pull request #15928 from velconia/imperative_backward_hooks
Imperative backward hooks
|
6 years ago |
Yiqun Liu
|
1616c32acf
|
Add the include of cudnn.h to enable the use of CUDNN_VERSION. (#15961)
test=develop
|
6 years ago |
|
Yiqun Liu
|
798925453e
|
Revert "Optimize while_op when is_test is true. (#15811)" (#15968)
test=develop
|
6 years ago |
flame
|
b187e3728e
|
add anakin fc op converter (#15965)
|
6 years ago |
minqiyang
|
e5f3435dd5
|
Add missing headers
test=develop
|
6 years ago |
|
minqiyang
|
fa1ff1d2f1
|
reduce ut time
test=develop
|
6 years ago |
|
Yiqun Liu
|
87248281f7
|
Fix error in CUDA kernel of beam_search. (#15957)
test=develop
|
6 years ago |
|
Tao Luo
|
c494f64a0f
|
Merge pull request #15941 from mozga-intel/mozga-intel/enable_mkldnn_framework
The flag of mkldnn engine is enabled iff it is necessary
|
6 years ago |
|
Tao Luo
|
344f098a34
|
Merge pull request #15963 from baojun-nervana/ngraph_v14
Fix lib64 issue on centos
|
6 years ago |
|
Tao Luo
|
4efdebc6f6
|
Merge pull request #15931 from yihuaxu/develop_2c5c7b2a7_gelu_mkl_opt
Optimize gelu operation with mkl erf
|
6 years ago |
baojun-nervana
|
b51e4dc0a4
|
fix lib64 test=develop
|
6 years ago |
tensor-tang
|
e5f9d3a47c
|
Merge pull request #15892 from tensor-tang/jit/sgd
refine sgd op
|
6 years ago |
|
Tao Luo
|
e6bab55f1b
|
Merge pull request #15959 from luotao1/infershape_refine
refine infershape of sequence_enumerate, hash and fuse_emb_seq_pool
|
6 years ago |
|
minqiyang
|
659a719315
|
increment resnet and ptbrnn's batch_num
test=develop
|
6 years ago |
|
minqiyang
|
50639fafdb
|
Polish code
test=develop
|
6 years ago |
ruri
|
72efef6358
|
Merge pull request #15887 from shippingwang/cosine_decay_op
add cosine decay op, test=develop
|
6 years ago |
|
flame
|
e40d56c3d3
|
anakin subgraph engine (#15774)
* add anakin subgraph engine
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* add initial op converter
* update
* update
* fix op register compile error
* update
test=develop
* update
|
6 years ago |
|
minqiyang
|
fe406b98c9
|
Polish code
test=develop
|
6 years ago |
|
Yiqun Liu
|
613d9d0756
|
Optimize while_op when is_test is true. (#15811)
test=develop
|
6 years ago |
xiaolil1
|
1abddd8d97
|
Optimize Quantize Op with primitive reuse. (#15929)
test=develop
|
6 years ago |
|
Tao Luo
|
7ec97a0a7e
|
Merge pull request #15930 from xiaolil1/dequantize-reuse
Optimize INT8 DeQuantize Op with primitive reuse.
|
6 years ago |
|
luotao1
|
34404f9c31
|
refine infershape of sequence_enumerate, hash and fuse_emb_seq_pool
test=develop
|
6 years ago |
Xin Pan
|
a63e2a0a4f
|
Merge pull request #15948 from panyx0718/api2
Add deprecation warning
|
6 years ago |
|
minqiyang
|
f469bb6b36
|
Polish code
test=develop
|
6 years ago |
|
minqiyang
|
ac88c62a5b
|
Reset output var's pre_op pointer when op was destructed
|
6 years ago |
