4329 Commits (2a9d74f67c39d46986868faa0700a705e7d57a24)

Author	SHA1	Message	Date
Yihua Xu	9b5017366a	Fix the format issue when 'X' is not nchw. (#17833) ... test=develop	6 years ago
Hongyu Liu	8062bd510c	Reshape support tensor attribute (#17781) ... * add reshape support tensor; test=develop * fix reshape bug; test=develop * change reshape attribute default value; test=develop * fix reshape input name; test=develop * fix reshape unitest; test=develop * check dim tensor shape; test=develop	6 years ago
Zeng Jinle	0a96ec699c	fix conv v7 workspace size limit error, test=develop (#17902)	6 years ago
Yihua Xu	14a32bf0c4	Fix the accuracy issue while using float precision to get the scale. (#17884) ... test=develop	6 years ago
gongweibao	fbbdc9ccad	Add backward and optimizer operator dependency pass. (#17746)	6 years ago
baojun	e2c1b7c354	[NGraph] cache compiled function instead test=develop (#17845)	6 years ago
Zhaolong Xing	ae576f3c68	fix: when use the load model from memory mode, the RAM occupy is high (#17788) ... test=develop	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) ... test=develop	6 years ago
pawelpiotrowicz	39bc8a55a4	[NGraph] Enable ngraph layer_norm operator (#17599) ... * Enable ngraph layer_norm operator test=develop * Disable/Enable cuda, new unit-test test=develop * Fix use_cudnn test=develop * Fixed test_layer test, new funciton is added test=develop * set use_cudnn by default test=develop	6 years ago
baojun	a4c528a31c	[NGraph] some ngraph updates to enable bert (#17739) ... * delay infershape test=develop * fall back subblock to paddle test=develop * fix edge cases test=develop * remove output duplicates test=develop * handle reshape2_grad infershape test=develop	6 years ago
baojun	7611208ab7	[NGraph] added gather_grad to ngraph test=develop (#17646)	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) ... * expand support tensor attribute; test=develop * fix bug ; test=develop * fix uni test bug; test=develop * fix copy bug; test=develop * refine expand_times default value; test=develop	6 years ago
Hongyu Liu	82358bfdc1	ont hot support tensor depth (#16972) ... * support some input tensor remain on cpu; test=develop * fix input = none; test=develop * fix unfound bug; test=develop * fix proto None case; test=develop * fix bug; test=develop * fix proto null bug; test=develop * remove conv check; test=develop * fix test bug; test=develop * move fill constant; test=develop * no change in proto; test=develop * fix bug; test=develop * change attr detph name; test=develop * remove remain cpu; test=develop * fix bug; test=develop * merge develop; test=develop * fix one_hot bug; test=develop * fix bug; test=develop * fix bug; test=develop * fix bug; test=develop * fix python api bug; test=develop	6 years ago
Brian Liu	7cfddf22c8	Optimize bilinear interpolate op with OpenMP (#17800) ... Refactor the code to be OpenMP friendly test=develop	6 years ago
wangchaochaohu	c10157a5df	revise the cudnn conv choose algorithm to improve the performance(mask rcnn benchmark) (#17753) ... * revise conv layer cudnn algo choose test=develop * update for code style test=develop * update for code style test=develop	6 years ago
mozga-intel	6a6bf597f7	[NGraph] Enable elementwise_div operator test=develop (#17515) ... * Enable elementwise_div operator test=develop * Fix update date test=develop	6 years ago
lidanqing	d7c5c2bd64	Add input format in Transpose GetHash (#17737) ... * fix the bug of mobilenet-ssd INT8 inference without overloading GetHash test=develop * remove the out_grad->format() in TransposeMKLDNNGradOpKernel test=develop	6 years ago
baojun	2c58f1a83c	[NGraph] Added lookup table to ngraph engine test=develop (#17647)	6 years ago
pawelpiotrowicz	bacc822492	[NGraph] Enable transpose ngraph operator (#17636) ... test=develop	6 years ago
baojun	90eae0b39a	[NGraph] Addded slice op to ngraph test=develop (#17648)	6 years ago
baojun	2fbaa5c075	[NGraph] added matmul op to ngraph engine test=develop (#17645)	6 years ago
Bai Yifan	bba57cdd82	Add deformable conv v2 op,test=develop (#17145) ... * unit commits, test=develop * update API.spec, test=develop	6 years ago
YishengCheng	bd15912d65	fix bug for ctr_reader for svm data (#17575) ... * fix bug for ctr_reader test=develop * fix svm data test=develop fix svm data test=develop	6 years ago
Yiqun Liu	8fd39f3e99	Enhance fused_elementwise_activation op and add python api in contrib.layers (#17236) ... * Enhance fused_elementwise_activation op. test=develop * Move the api fused_elementwise_activation to contrib. test=develop * Add including files. test=develop * Add the support of sigmoid in fused_elementwise_activetion op. * Update API.spec. test=develop	6 years ago
Yiqun Liu	2704479bb2	Optimize recurrent_op using Prepare and RunPreparedContext, avoiding create operators in every iter. (#17689) ... test=develop	6 years ago
pawelpiotrowicz	9b99876442	Enable less_than ngraph operator (#17642) ... * Enable less_than ngraph operator test=develop * Added compare unit-tests test=develop * Update: date && removed import test=develop	6 years ago
hutuxian	4ff87c049d	remove useless input 'Softmax@GRAD' from softmax_with_cross_entropy op (#17612)	6 years ago
pawelpiotrowicz	70a887af63	[NGraph] Add reduce_sum operator for Ngraph (#17450) ... test=develop	6 years ago
baojun	29baca0dd8	add depthwise_conv2d op to ngraph engine (#17454) ... * add depthwise_conv2d test=develop * use cpu for ngraph test=develop	6 years ago
gongweibao	0d561ef442	fix 2dconn test=develop (#17681)	6 years ago
mozga-intel	ccf9e2327b	[Lite] Enable cast operator test=develop (#17294)	6 years ago
Yiqun Liu	5782dddad0	Optimize the concat and split kernel for specical cases when the number of inputs/outputs is 2 (#17415) ... * Optimize the concat and split kernel for special cases that the number of inputs/outputs is 2. test=develop * Refine codes. test=develop * Correct the condition. test=develop * Move the define of tmp_data outside the if statement. * Print the cudnn minor version. test=develop * Fix the case when in_num/o_num is 1 in concat/split op. test=develop * Remove const_cast. test=develop	6 years ago
lidanqing	04b6c29ee0	Improve mobilenetv2 INT8 performance by using INT8 relu as post-op (#17570) ... * add INT8 conv+relu6 fuse and enbale mobilentv2 INT8 test test=develop * change fasle and 0.0 to fuse_brelu and brelu_threshold test=develop change the "fuse_relu||fuse_brelu" to "unsigned_output" test=develop * Use relu instead of brelu as INT8 post-op because INT8 brelu is not enabled in mkldnn v0.18 test=develop * continuous-integration fix test=develop	6 years ago
Tao Luo	962eed6f82	Revert "Enable SQRT operator for the nGraph Bridge (#17549)" (#17680) ... This reverts commit f34830e2aa.	6 years ago
Krzysztof Binias	f34830e2aa	Enable SQRT operator for the nGraph Bridge (#17549) ... * Enable sqrt operator for the nGraph Bridge. test=develop * Update activation_op.h	6 years ago
Sylwester Fraczek	96845d2168	add Concat quantization (#17448) ... * add Concat quantization add unit test for quantizing concat fix for wrong value when the input is not in map of calculated scales add use_quantizer to concat_op.cc add scale_algo rules for concat test=develop * missing fix for multiple inputs quantize-squash * wojtuss review fix: adding comment test=develop	6 years ago
gongweibao	65bbf950ee	Add multi-ncclcomm and 2D ncclallreduce support. (#17263)	6 years ago
Krzysztof Binias	b1bd483a7d	[NGraph] Enable gelu operator for the nGraph Bridge. (#17547) ... test=develop	6 years ago
chengduo	343017324e	Polish Print Op (#17651) ... * enhance print	6 years ago
Zeng Jinle	4aa931dd85	Code clean of Allocator (#17602) ... * Revert "Revert "Fix allocator bug"" This reverts commit 174d0d0b90. * Revert "fix travis ci" This reverts commit 5656fa9f7c. test=develop * add inlined_vector.h, test=develop * add inlined_vector_test,test=develop * clean code of allocator,test=develop * delete zero_size_allocator.h,test=develop * fix failed unittest,test=develop	6 years ago
Guo Sheng	430e25654b	Fix the usage of out_grad lod in sequence_slice_op. (#17625) ... test=develop	6 years ago
hutuxian	1670db5e86	Gather Op Index Support int64_t datatype (#17610) ... * gather_op support int64_t index by adding a template typename * add UT and rename typename test=develop	6 years ago
mozga-intel	2b83d75bfa	Enable elementwise pow operator for ngraph (#17526)	6 years ago
Zhaolong Xing	61221ebc28	TRT: Support set dynamic range in int8 mode. (#17524) ... * fluid int8 train and trt int8 predict align. trt int8 predict init op converter * 2. align fluid int8 train and trt int8 inference. enhance quant dequant fuse pass enhance op converter, trt engine, trt engine op, trt subgraph pass. * 3. add delete_quant_dequant_pass for trt test=develop * 4. add the missing file test=develop * 5. i modify the c++ interface, but forget to modify the pybind code fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter test=develop	6 years ago
Michał Gallus	0c39b97b4e	[MKL-DNN] Add Fully Connected Op for inference only(#15226) ... * fuse mul and elementwise add to fc * Reimplement the FC forward operator * Fix FC MKLDNN integration by transposing weights * Add FC MKLDNN Pass test=develop * FC MKLDNN Pass: change memcpy to std::copy * Fix MKLDNN FC handling of mismatch input and weights dims * Lower tolerance for MKL-DNN in resnet50 test test=develop * Adjust FC to support MKLDNN Op placement test=develop * Adjust Placement Op to set use_mkldnn attribute for graph test=develop * MKLDNN FC: fix weights format so that gemm version is called test=develop * FC MKLDNN: Remove tolerance decrease from tester_helper * FC MKL-DNN: Refactor the code, change input reorder to weight reorder * MKL-DNN FC: Introduce operator caching test=develop * FC MKL-DNN: Fix the tensor type in ExpectedKernelType test=develop * FC MKL-DNN: fix style changes test=develop * FC MKL-DNN: fallback to native on non-supported dim sizes test=develop * FC MKLDNN: fix CMake paths test=develop * FC MKLDNN: Refine placement pass graph mkldnn attribute test=develop * Fix Transpiler error for fuse_conv_eltwise test=develop * Fix missing STL includes in files test=develop * FC MKL-DNN: Enable new output size computation Also, refine pass to comply with newest interface. test=develop * FC MKL-DNN: enable only when fc_mkldnn_pass is enabled * FC MKL-DNN: Allow Weights to use oi or io format * FC MKL-DNN: Adjust UT to work with correct dims test=develop * Enable MKL DEBUG for resnet50 analyzer test=develop * FC MKL-DNN: Improve Hashing function test=develop * FC MKL-DNN: Fix shape for fc weights in transpiler * FC MKL-DNN: Update input pointer in re-used fc primitive * Add log for not handling fc fuse for unsupported dims test=develop * FC MKL-DNN: Move transpose from pass to Op Kernel test=develop * FC MKL-DNN: Disable transpose in unit test test=develop * FC MKL-DNN: Remove fc_mkldnn_pass from default list * Correct Flag for fake data analyzer tests test=develop * FC MKL-DNN: Add comment about fc mkldnn pass disablement test=develop * FC MKL-DNN: Disable fc in int8 tests test=develop	6 years ago
Krzysztof Binias	e9216d0602	Enable logical operators for the nGraph Bridge. (#17543) ... test=develop	6 years ago
Yibing Liu	e8990e64f6	Fix trust ratio in lamb (#17614) ... test=develop	6 years ago
chengduo	b5f4d5ed0e	Add broadcast operators (#17503) ... * This PR adds broadcast for multi-process. And it could be used in dynamic graph to broadcast parameters.	6 years ago
Sylwester Fraczek	bccb0ba49a	fix quantize_squash_pass segfault when no tensor linked to Bias (#17292) ... * fix quantize_squash_pass segfault when there is no tensor linked do Bias input test=develop * add googlenet test test=develop * fix concat CreateKey not using input format test=develop	6 years ago