summaryrefslogtreecommitdiff
path: root/caffe2
AgeCommit message (Expand)AuthorFilesLines
2019-04-01use acc16 only when n>128 and k>128 in Skylake (#18672)Jongsoo Park1-6/+18
2019-04-01Move ideep singleton registration to ATen from C2. (#18335)Gregory Chanan1-1/+1
2019-03-31handle a rare case of histogram min is inf/nan (#18239)Jongsoo Park2-6/+14
2019-03-31Adding quantized tensor shape/type info support for caffe2=>glow in caffe2 si...Rui Zhu13-43/+261
2019-03-30Check kernel against function schema in c10 op registration (#18256)Sebastian Messmer1-1/+1
2019-03-30Add functor- and function-based kernel registration API (#18162)Sebastian Messmer52-1324/+860
2019-03-30New operator registration MVP (#18161)Sebastian Messmer1-49/+58
2019-03-29support pre-convert filter format for mkldnn training mode and change 'Optimi...Cheng,Penghui12-31/+292
2019-03-29Tensor construction codemod(raw_mutable_data) (#16373)Jerry Zhang27-129/+116
2019-03-29Fix bug in tensor feed which caused crash due to wrong tensor type (#18552)Gu, Jinghui1-3/+5
2019-03-29register BoxWithNMSLimit with C10Yanghan Wang3-44/+192
2019-03-29Manual hipify caffe2/distributed and rocm update (no hcc modules support) (#1...Xiaodong Wang2-0/+20
2019-03-29Change dnnlowp log level from warning to v2 (#18576)Summer Deng1-13/+12
2019-03-29Optimize relu op on GPU (#18506)Xiaomeng Yang2-83/+74
2019-03-28Automatic update of fbcode/onnx to fb1a80692c1ab0bd27b1072f2e7bffacba336777 (...Lu Fang1-0/+1
2019-03-28Resubmit PR-18512: Improved onnx export for 3 onnx ops (#18571)bddppq7-4/+40
2019-03-28Implement rotated generate_proposals_op without opencv dependency (CPU version)Jing Huang4-212/+242
2019-03-28Use SetOutputTensor instead of copying outputs manually (#17770)Ahmed Aly1-13/+5
2019-03-28Inference LSTM integration test (#18559)Ahmed Aly1-0/+80
2019-03-28Revert D14635130: Improved onnx export for 3 onnx ops.Junjie Bai3-19/+2
2019-03-28Improved onnx export for 3 onnx ops. (#18512)Benoit Steiner3-2/+19
2019-03-27add extra info for the auto gen sum opsXianjie Chen2-1/+9
2019-03-27Skip tests if C2/ONNX models cannot be read (#18494)Min Ni5-147/+46
2019-03-27Add qtensors in caffe2 protobuf argument (#18486)zrphercule1-0/+1
2019-03-26Back out "Revert D14613517: [pytorch][PR] Updating onnxtrt submodule to maste...Li Yu2-2/+2
2019-03-26Move weight offload inside backend construction functor (#18385)Yinghai Lu2-38/+39
2019-03-26Revert D14613517: [pytorch][PR] Updating onnxtrt submodule to master branchLi Yu2-2/+2
2019-03-26Fix direct comparison of OperatorDef proto structs (#18466)Junjie Bai1-1/+12
2019-03-26Fix typo in Github links in elementwise_ops_schema.cc (#18018)Sameer Indarapu1-3/+3
2019-03-26Updating onnxtrt submodule to master branchKevin Chen2-2/+2
2019-03-26Expose c10 operators to caffe2 by operator name (#18160)Sebastian Messmer21-48/+62
2019-03-26Move math::Axpy function to elementwise lib (#18316)Xiaomeng Yang11-606/+575
2019-03-26Resolving comments from Bool Tensor for CPU PR (#18165)Iurii Zdebskyi2-5/+5
2019-03-25Change deprecated IntList to IntArrayRefXiang Gao1-1/+1
2019-03-25caffe2 - support flaky operator tests for caffe2 build (#18155)Duc Ngo2-1/+28
2019-03-25Fix caffe2 build with BLAS=OpenBLAS (#18422)nihui2-0/+2
2019-03-25Add more options to the quantization model exporter (#18383)Summer Deng1-15/+17
2019-03-23Revert D14446895: [C2] Implement rotated generate_proposals_op without opencv...Edward Yang5-156/+210
2019-03-22Implement rotated generate_proposals_op without opencv dependency (1.8x faste...Jing Huang5-210/+156
2019-03-22Fix alignment issues for Fake BFP16 fp32 -> bfp16 rounding routines (#18321)Jianyu Huang1-1/+1
2019-03-22Caffe2: crash op (#18207)Alexander Sidorov1-0/+25
2019-03-22caffe2 - Util to cleanup external inputs and outputs from a NetDef (#18194)Duc Ngo3-3/+94
2019-03-22Optimize MomentumSGDUpdate maximum block size and make it templatedBilge Acun1-24/+58
2019-03-22Verify def before infer fensor (#18129)Gerard Goossen2-4/+9
2019-03-22add more Python interface functions to make quantization simpler (#18246)Jongsoo Park1-0/+89
2019-03-22add fbgemm fp16 (fbfcpacked) support, add global_init_net in predictor_export...Weiyi Zheng2-2/+29
2019-03-22Automatic update of fbcode/onnx to c05f2ae412daf8fd64136ca354b97ccf73e0ea6c (...Lu Fang2-1/+7
2019-03-21Replace the remaining usages of IntList in caffe2 to IntArrayRefJunjie Bai3-3/+3
2019-03-21Blacklist certain op types when doing bound shape inference (#18290)Yinghai Lu2-22/+19
2019-03-21Allow registering same operator schema multiple times (#18038)Sebastian Messmer1-4/+4
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-26 12:10:21 +0000