Commit Graph

15292 Commits (82bfa0a5ba5a4e54c8200c12f9f59716d6044e72)

Author SHA1 Message Date
jerrywgz aab4d12c0e
refine GetExpectedKernelType in conat op, test=develop (#17934)
6 years ago
Zeng Jinle 3ece61f71e
Remove attribute in Allocator::Allocate (#17878)
6 years ago
Yibing Liu 33d1e56506
Enable seq_pool op to accept len 0 input (#17284)
6 years ago
Yihua Xu 9b5017366a Fix the format issue when 'X' is not nchw. (#17833)
6 years ago
Hongyu Liu 8062bd510c
Reshape support tensor attribute (#17781)
6 years ago
gongweibao 972c54cd70
Fix FLAGS_fuse_parameter_memory_size unit from Bytes to MBytes. (#17924)
6 years ago
Zeng Jinle 0a96ec699c
fix conv v7 workspace size limit error, test=develop (#17902)
6 years ago
Jiabin Yang 4d5f6937c3
Feature/refine api for dygraph (#17907)
6 years ago
gongweibao dd4cd352c7
Fix sync_batch_norm_op ncclallreduce error! (#17918)
6 years ago
whs 5df65e506d
Add Ligth-NAS for PaddleSlim (#17679)
6 years ago
Zeng Jinle 3925bd81e8
Fix cuda/cudnn version detection error (#17853)
6 years ago
Yihua Xu 14a32bf0c4 Fix the accuracy issue while using float precision to get the scale. (#17884)
6 years ago
gongweibao fbbdc9ccad
Add backward and optimizer operator dependency pass. (#17746)
6 years ago
mozga-intel c1379bf238 [NGraph] Bert model for a capi, ngraph's support test=develop (#17844)
6 years ago
baojun e2c1b7c354 [NGraph] cache compiled function instead test=develop (#17845)
6 years ago
石晓伟 d008260fa8
update the initialization of anakin subgraph (#17880)
6 years ago
Zhaolong Xing ae576f3c68
fix: when use the load model from memory mode, the RAM occupy is high (#17788)
6 years ago
Zhaolong Xing 5efe8c7287
fix bug: the lod_tensor_to_array op will aplly a new var but not release when dong inference (#17856)
6 years ago
Jiabin Yang 022dfed4fc
Add optimizer save and load (#16986)
6 years ago
wopeizl 453a49b1bc
Make ParallelExecutor support Windows GPU (#17787)
6 years ago
pawelpiotrowicz 39bc8a55a4 [NGraph] Enable ngraph layer_norm operator (#17599)
6 years ago
翟飞跃 993c703bcc INT8 MKL-DNN v2 integrate to slim (#17634)
6 years ago
wopeizl 841553e13f
use pyreader to read data in dygraph mode (#17314)
6 years ago
chengduo 5436d66667
close socket connect (#17862)
6 years ago
baojun a4c528a31c [NGraph] some ngraph updates to enable bert (#17739)
6 years ago
Jiabin Yang 3d3f5506d2
Feature/Fix recurrent usage of Varbase in Dygraph (#17838)
6 years ago
Zeng Jinle 674e0ce2d6
Use Python C-API to speed up dygraph trace (#17837)
6 years ago
tianshuo78520a 47cc1b51ad Change Linux CI check API
6 years ago
jerrywgz 5e4f99dd74
refine doc for prelu (#17810)
6 years ago
chengduo d1169afaa3
remove InstallFailureSignalHandler (#17828)
6 years ago
chengduo 437520474c
fix DropLocalExeScopes (#17829)
6 years ago
Leo Zhao 50326563d5 enable mkldnn primitive reuse for platform reorder (#17826)
6 years ago
baojun 7611208ab7 [NGraph] added gather_grad to ngraph test=develop (#17646)
6 years ago
tensor-tang 557452e778
update and polish hash op doc (#17809)
6 years ago
jerrywgz 92d9bdfce2
fix api doc in slice op, test=develop (#17804)
6 years ago
Hongyu Liu dfec676270
expand op supprt tensor attribute (#17773)
6 years ago
Jiabin Yang 3b70f870e2
Using Smart pointer to optimizer memory usage of dyGraph (#17768)
6 years ago
Hongyu Liu 82358bfdc1
ont hot support tensor depth (#16972)
6 years ago
Brian Liu 7cfddf22c8 Optimize bilinear interpolate op with OpenMP (#17800)
6 years ago
Yibing Liu d6d33fd748
Add update method for ema (#17812)
6 years ago
wangchaochaohu c10157a5df
revise the cudnn conv choose algorithm to improve the performance(mask rcnn benchmark) (#17753)
6 years ago
chengduo 863c75168c
polish error doc (#17772)
6 years ago
Tao Luo e089e454a1
make omp thread num default 1 after inference run (#17801)
6 years ago
mozga-intel 6a6bf597f7 [NGraph] Enable elementwise_div operator test=develop (#17515)
6 years ago
Huihuang Zheng 931698a54a
Modify doc of program_guard, py_reader, data, and clone (#17727)
6 years ago
lidanqing d7c5c2bd64 Add input format in Transpose GetHash (#17737)
6 years ago
tangwei12 659b72a97c
fix document of python api get_startup_program() (#17764)
6 years ago
AIFollowers 93de124cec modify some initializer api (#17301)
6 years ago
guru4elephant d52391094d
fix prepare context redundant code problem, optimize executor by cach… (#17743)
6 years ago
baojun 2c58f1a83c [NGraph] Added lookup table to ngraph engine test=develop (#17647)
6 years ago