summaryrefslogtreecommitdiff
path: root/caffe2
AgeCommit message (Expand)AuthorFilesLines
2019-02-15merge fully_connected_rowwise_dnnlowp_op into fully_connected_dnnlowp_op (#17...Jongsoo Park13-569/+246
2019-02-15bug fix when we prepack weight and bias together (#17145)Jongsoo Park2-11/+14
2019-02-15caffe2: fix PinnedCPUAllocator cudaHostRegister() leak (#16340)Brian W. Hart1-0/+4
2019-02-15Updated bbox_transform and nms unit test for caffe2 ops. (#16722)Peizhao Zhang2-6/+57
2019-02-14add pre-packing operation in README.md (#17151)Jongsoo Park1-0/+47
2019-02-14Minor fix of the histogram observer in FBL eval flows (#17118)Summer Deng1-6/+8
2019-02-14Create BackendTransformerBase to host common functions used for backend lower...Yinghai Lu6-190/+238
2019-02-14Apply modernize-use-override (2nd iteration)Michael Liu27-55/+65
2019-02-14Use new constructor in USE_SIMPLE_CTOR_DTOR (#17080)Sebastian Messmer1-2/+2
2019-02-14Remove fake inference for shape info in ONNXIFI transform (#17046)Yinghai Lu4-83/+39
2019-02-14Moderate the dim type after LengthsRangeFill (#17096)Yinghai Lu2-0/+40
2019-02-14Add support of count_include_pad and test end to end test for AveragePool (#1...Dwarak Rajagopal1-61/+2
2019-02-13Clean up Storage/StorageImpl constructors (#16948)Dmytro Dzhulgakov1-2/+2
2019-02-13Apply modernize-use-override - 2/2Michael Liu19-34/+37
2019-02-13PyTorch model metadata. (#16275)Pritam Damania1-4/+0
2019-02-13Separate reduce functions from math (#16929)Xiaomeng Yang18-1460/+1002
2019-02-13Support FC (Caffe2) -> Gemm (ONNX) with variable input shape. (#16184)Tongliang Liao2-31/+81
2019-02-13Make timeout in resnet50_trainer configurable (#17058)Junjie Bai1-5/+12
2019-02-13Support conversion from Caffe2 MergeDim to ONNX Reshape + Squeeze. (#16189)Tongliang Liao4-1/+68
2019-02-13Add more debugging facilities to ONNXIFI transform (#17043)Yinghai Lu1-3/+12
2019-02-12unify c2 and TH allocator (#16892)Dmytro Dzhulgakov5-250/+75
2019-02-12Remove second output of Reshape during ONNXIFI transform (#17027)Yinghai Lu4-7/+64
2019-02-12Fold col offsets into bias; optimize A symmetric quant (#16942)Jongsoo Park4-64/+170
2019-02-12Register CUDA kernels for caffe2 operators (#16691)Sebastian Messmer3-12/+119
2019-02-12Extract ShapeInfo and some util functions into a separate file. (#17025)Ying Zhang4-21/+51
2019-02-12Allow customization of blob node in net_drawer (#16915)Yinghai Lu5-23/+34
2019-02-12Ignore unknown_shaped tensor in bound shape inference (#16916)Yinghai Lu2-13/+20
2019-02-12Export ReduceMean/ReduceFrontMean/ReduceBackMean (Caffe2) to ReduceMean (ONNX...Tongliang Liao5-3/+134
2019-02-12Fix AddAdjustBatchOp (#16997)Yinghai Lu1-10/+20
2019-02-12More docs for methods in operator.hEdward Yang1-0/+12
2019-02-11Fix NERPredictor for zero initializationDmytro Dzhulgakov1-5/+5
2019-02-11Keep weights name unchanged during SsaRewrite (#16932)Kimish Patel5-21/+50
2019-02-11Expose GenerateProposals to PyTorchSebastian Messmer3-3/+68
2019-02-11Expose BBoxTransform to pytorchSebastian Messmer3-2/+142
2019-02-11Minimize templated code in caffe2 operator wrapper (#16965)Sebastian Messmer1-6/+25
2019-02-11Catch cudaError_t return val (nodiscard in rocm) (#16399)Xiaodong Wang1-2/+2
2019-02-10Int8GivenTensorFill Operator Schema fix typo (#16204)eyyub.sari@epitech.eu1-2/+2
2019-02-09Change the default image size from 227 to 224 in resnet50 trainer (#16924)Junjie Bai1-1/+1
2019-02-08Make the exception raised from "numpy.dtype(numpy.void, (INT,))" less cryptic...Chandler Zuo2-0/+16
2019-02-08Revert D13970381: [caffe2] Add visibility to registry class to fix ubsan errorBram Wasti1-10/+9
2019-02-08Extend Net.RunAllOnGPU() to support RecurrentNetwork op (#15713)Nikita Shulga2-4/+40
2019-02-08Impl ExpandDims op and fallback to CPU if needed (#15264)Gu, Jinghui5-96/+265
2019-02-08Add visibility to registry class to fix ubsan error (#16792)Bram Wasti1-9/+10
2019-02-08Remove Legacy entry point. (#16721)Edward Yang2-5/+29
2019-02-08Delete duplicate copy of THCCachingAllocator (round two). (#16615)Edward Yang3-336/+3
2019-02-07Don't automatically handle context parameter (#16867)Sebastian Messmer2-21/+26
2019-02-07Support onnxifi with partially shaped inferred net (#16877)Yinghai Lu1-2/+10
2019-02-07Specialize LengthsRangeFill and SparseLengthsWeightedSum in bound shape infer...Yinghai Lu2-6/+42
2019-02-07Activation histogram net observer with multiple histogram files as output (#1...Summer Deng2-4/+18
2019-02-07Separate elementwise level2 math functions (#16753)Xiaomeng Yang25-737/+1038
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-30 10:28:55 +0000