mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-06-12 12:22:51 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
31,023 Commits 6 Branches 128 Tags 3.4 GiB
cca4c47781
Commit Graph

162 Commits

Author SHA1 Message Date
Alexander Alekhin
cca4c47781 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2021-10-08 11:05:45 +00:00
Alexander Alekhin
724e04e979 dnn(ocl4dnn): add extra checks to convolution layer 
- prevent running code over unsupported/non-tested configurations
- prevent integer div by zero
 2021-10-07 23:18:32 +00:00
SamFC10
fa90e14b06 int8 layers and 8-bit quantization support 2021-08-19 09:56:47 +05:30
HAN Liutong
aaca4987c9
Merge pull request #20287 from hanliutong:dev-rvv-0.10 
Optimization of DNN using native RISC-V vector intrinsics.

* Use RVV to optimize fastGEMM (FP32) in DNN.

* Use RVV to optimize fastGEMM1T in DNN.

* Use RVV to optimize fastConv in DNN.

* Use RVV to optimize fastDepthwiseConv in DNN.

* Vectorize tails using vl.

* Use "vl" instead of scalar to handle small block in fastConv.

* Fix memory access out of bound in "fastGEMM1T".

* Remove setvl.

* Remove useless initialization.

* Use loop unrolling to handle tail part instead of switch.
 2021-08-11 01:16:03 +03:00
Alexander Alekhin
3e1673e8b2 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2021-04-01 09:54:57 +00:00
Vitaly Tuzov
aab62aa6dd
Merge pull request #18952 from terfendail:wui_doc 
* Updated UI documentation to address WUI

* Added documentation for vx_ calls

* Removed vx_store operation overload

* Doxyfile updated to enable wide UI

* Enable doxygen documentation for vx_ WUI functions

* Wide intrinsics definition rework

* core: fix SIMD C++ emulator build (supports 128-bit only)
 2021-03-30 16:18:03 +00:00
Alexander Alekhin
ca8c3dd9b5 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2021-03-22 12:05:23 +00:00
Liubov Batanina
c0dd82fb53
Merge pull request #19632 from l-bat:lb/ie_arm_target 
Added OpenVINO ARM target

* Added IE ARM target

* Added OpenVINO ARM target

* Delete ARM target

* Detect ARM platform

* Changed device name in ArmPlugin

* Change ARM detection
 2021-03-20 11:20:02 +00:00
Sergey Slashchinin
e2949c7d0a Align 3.4 branch with master 2021-01-29 23:48:08 +03:00
Sergei Slashchinin
ea41f89b40
Merge pull request #19058 from sl-sergei:cuda_1d 
Conv1D and Pool1D for CUDA backend

* CUDA-independent changes

* Add Conv1D and Pool1D for CUDA backend

* CUDA-independent changes

* Fix typo

* fix comment

* Update fix

* make changes more correct for pooling layer

* Minor fixes for review

* Split skip blocks
 2021-01-21 22:16:56 +00:00
Alexander Alekhin
624d532000 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-12-17 21:05:34 +00:00
Alexander Alekhin
c240355cc6 dnn(ocl): avoid mess FP16/FP32 in convolution layer 2020-12-15 08:51:24 +00:00
Alexander Alekhin
de385009ae Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-12-09 18:09:00 +00:00
Alexander Alekhin
00f36a3149 dnn: prefer to use v_fma() instead of v_c += v_a * v_b 2020-12-05 11:51:03 +00:00
Omar Alzaibaq
a316b11aaa
Merge pull request #18220 from Omar-AE:hddl-supported 
* added HDDL VPU support

* changed to return True in one line if any device connected

* dnn: use releaseHDDLPlugin()

* dnn(hddl): fix conditions
 2020-11-17 19:47:24 +00:00
Alexander Alekhin
a7c150ec66 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-11-13 22:29:14 +00:00
Sergei Slashchinin
61144f935e
Merge pull request #18783 from sl-sergei:fix_conv1d 
Add support for Conv1D on OpenCV backend

* Add support for Conv1D on OpenCV backend

* disable tests on other targets/backends

* Fix formatting

* Restore comment

* Remove unnecessary flag and fix test logic

* Fix perf test

* fix braces

* Fix indentation, assert check and remove unnecessary condition

* Remove unnecessary changes

* Add test cases for variable weights and bias

* dnn(conv): fallback on OpenCV+CPU instead of failures

* coding style
 2020-11-13 22:22:10 +00:00
Alexander Alekhin
1b443219ed Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-10-09 20:09:26 +00:00
Alexander Alekhin
cdcf7e62f3 dnn(opencl): bypass unsupported fusion cases 2 2020-10-09 18:59:08 +00:00
Alexander Alekhin
718dd9f170 dnn(opencl): bypass unsupported fusion cases 2020-10-09 12:33:06 +00:00
NesQl
3fc1487cc9
Merge pull request #18323 from liqi-c:tengine-lite-update 
Tengine lite update

* update tengine

* Modify for arm32 build.

* format optimization

* add teng_ befor some tengine api

* update graph_t to teng_graph_t

* update graph_t to teng_graph_t

* Code structure optimization

* optimization

* optimization

* remove space

* update tengine url

Co-authored-by: liqi <qli@openailab.com>
 2020-09-23 09:34:29 +00:00
Alexander Alekhin
1f2c83845d backport: checks and fixes from static code analyzers results 
original commit: 71f665bd8c
 2020-09-02 19:05:47 +00:00
Alexander Alekhin
71f665bd8c checks and fixes from static code analyzers results 2020-09-02 21:59:34 +03:00
Alexander Alekhin
fa25faa2d2 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-08-06 14:15:52 +00:00
Vadim Pisarevsky
1537ecd931 * added depth-wise convolution; gives ~20-30% performance improvement in MobileSSD networks 
* hopefully, eliminated compile warnings, errors, as well as failure in one test

* * fixed a few typos
* decreased buffer size in some cases
* added more optimal im2row branch in the case of 1x1 convolutions
* tuned fastConv to reduce the number of passes over arrays

backport of commit 77b01deb80
 2020-08-04 17:34:48 +00:00
Liubov Batanina
d695208727
Merge pull request #17967 from l-bat:non_const_weights_for_conv 
* Supported convolution with non-const weights

* Fix opencl blobs

* Update tests
 2020-08-03 18:02:49 +00:00
Vadim Pisarevsky
77b01deb80
Merge pull request #17858 from vpisarev:dnn_depthwise_conv 
* added depth-wise convolution; gives ~20-30% performance improvement in MobileSSD networks

* hopefully, eliminated compile warnings, errors, as well as failure in one test

* * fixed a few typos
* decreased buffer size in some cases
* added more optimal im2row branch in the case of 1x1 convolutions
* tuned fastConv to reduce the number of passes over arrays
 2020-08-01 15:05:05 +03:00
Yashas Samaga B L
f53f491cd2
Merge pull request #17939 from YashasSamaga:cuda4dnn-fix-eltwise-fusion 
* fix eltwise fusion segfault, more eltwise fusions, fix power fusion

* add assertion
 2020-08-01 15:03:07 +03:00
Yashas Samaga B L
d0e6d2438c
Merge pull request #17363 from YashasSamaga:cuda4dnn-eltwise-fusion2 
cuda4dnn(conv): fuse eltwise with convolutions

* fuse eltwise with convolutions

* manually rebase to avoid bad git merge
 2020-07-09 16:02:21 +03:00
Alexander Alekhin
88d8a48b09 Merge pull request #17374 from alalek:dnn_fix_build 2020-05-25 18:46:15 +00:00
Alexander Alekhin
73aa5f567b dnn: *_DENORMALS_ZERO_MODE is defined for SSE3 2020-05-25 17:55:36 +00:00
Alexander Alekhin
21e28adb87 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-05-22 19:50:14 +00:00
Dmitry Kurtaev
68d59a2913 Flush to zero Convolution denormal weights 2020-05-15 23:44:34 +03:00
Yashas Samaga B L
d981d04c76
Merge pull request #17200 from YashasSamaga:cuda4dnn-general-opt1 
cuda4dnn: optimizations for swish, mish, sigmoid, region, resize based ops, transpose, identity-conv fusion

* bunch of optimizations

* more accurate implementation for mish
 2020-05-09 17:20:30 +00:00
Alexander Alekhin
9b3be01b83 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-03-09 20:27:34 +00:00
NesQl
0bcdf7d03e
Merge pull request #16724 from liqi-c:3.4-tengine 
* Add Tengine support .

* Modify printf to CV_LOG_WARNING

* a few minor fixes in the code

* Renew Tengine version

* Add header file for CV_LOG_WARNING

* Add #ifdef HAVE_TENGINE in tengine_graph_convolution.cpp

* remove trailing whitespace

* Remove trailing whitespace

* Modify for compile problem

* Modify some code style error

* remove whitespace

* Move some code style problem

* test

* add ios limit and build problem

* Modified as alalek suggested

* Add cmake 2.8 support

* modify cmake 3.5.1 problem

* test and set BUILD_ANDROID_PROJECTS OFF

* remove some compile error

* remove some extra code in tengine

* close test.

* Test again

* disable android.

* delete ndk version judgement

* Remove setenv() call . and add License information

* Set tengine default OFF. Close test .

Co-authored-by: Vadim Pisarevsky <vadim.pisarevsky@gmail.com>
 2020-03-09 14:59:23 +00:00
Alexander Alekhin
124bf8339f dnn(IE): use HAVE_DNN_IE_NN_BUILDER_2019 for NN Builder API code 
- CMake option: OPENCV_DNN_IE_NN_BUILDER_2019
 2020-03-03 08:07:54 +00:00
Alexander Alekhin
29d214474f dnn(IE): use HAVE_DNN_IE_NN_BUILDER_2019 for NN Builder API code 
- CMake option: OPENCV_DNN_IE_NN_BUILDER_2019
 2020-03-03 07:45:09 +00:00
Alexander Alekhin
560f85f8e5 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-01-28 14:26:57 +03:00
Liubov Batanina
a3ae69893c Extend nGraph Deconvolution layer support 2020-01-23 15:10:42 +03:00
Yashas Samaga B L
17c485eb03 Merge pull request #16092 from YashasSamaga:cuda4dnn-conv-act-fuse 
cuda4dnn: fuse activations with convolutions

* fuse ReLU, ReLU6, TanH, Sigmoid with conv

* fix OpenCL errors

* improve ReLU, add power, swish and mish

* fix missing fusion entries

* fix handling of unsetAttached

* remove whole file indentation

* optimize power = 1.0, use IDENTITY instead of NONE

* handle edge case: change backend and then clear
 2019-12-14 22:26:58 +03:00
Alexander Alekhin
92b9888837 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-12-12 13:02:19 +03:00
Alexander Alekhin
939099b9ce Merge pull request #16107 from dkurt:dnn_ie_ngraph_v1_conv 2019-12-10 12:10:50 +00:00
Dmitry Kurtaev
fe77223dee Modify nGraph's ConvolutionBackpropData and GroupConvolution 2019-12-10 14:14:00 +03:00
Dmitry Kurtaev
c2ca3ee2fa Fix weights fusion for Convolution and Deconvolution layers in nGraph 2019-12-09 19:06:47 +03:00
Alexander Alekhin
4b0132ed7a Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-12-02 16:26:52 +03:00
Lubov Batanina
7523c777c5 Merge pull request #15537 from l-bat:ngraph 
* Support nGraph

* Fix resize
 2019-12-02 16:16:06 +03:00
Yashas Samaga B L
613c12e590 Merge pull request #14827 from YashasSamaga:cuda4dnn-csl-low 
CUDA backend for the DNN module

* stub cuda4dnn design

* minor fixes for tests and doxygen

* add csl public api directory to module headers

* add low-level CSL components

* add high-level CSL components

* integrate csl::Tensor into backbone code

* switch to CPU iff unsupported; otherwise, fail on error

* add fully connected layer

* add softmax layer

* add activation layers

* support arbitary rank TensorDescriptor

* pass input wrappers to `initCUDA()`

* add 1d/2d/3d-convolution

* add pooling layer

* reorganize and refactor code

* fixes for gcc, clang and doxygen; remove cxx14/17 code

* add blank_layer

* add LRN layer

* add rounding modes for pooling layer

* split tensor.hpp into tensor.hpp and tensor_ops.hpp

* add concat layer

* add scale layer

* add batch normalization layer

* split math.cu into activations.cu and math.hpp

* add eltwise layer

* add flatten layer

* add tensor transform api

* add asymmetric padding support for convolution layer

* add reshape layer

* fix rebase issues

* add permute layer

* add padding support for concat layer

* refactor and reorganize code

* add normalize layer

* optimize bias addition in scale layer

* add prior box layer

* fix and optimize normalize layer

* add asymmetric padding support for pooling layer

* add event API

* improve pooling performance for some padding scenarios

* avoid over-allocation of compute resources to kernels

* improve prior box performance

* enable layer fusion

* add const layer

* add resize layer

* add slice layer

* add padding layer

* add deconvolution layer

* fix channelwise  ReLU initialization

* add vector traits

* add vectorized versions of relu, clipped_relu, power

* add vectorized concat kernels

* improve concat_with_offsets performance

* vectorize scale and bias kernels

* add support for multi-billion element tensors

* vectorize prior box kernels

* fix address alignment check

* improve bias addition performance of conv/deconv/fc layers

* restructure code for supporting multiple targets

* add DNN_TARGET_CUDA_FP64

* add DNN_TARGET_FP16

* improve vectorization

* add region layer

* improve tensor API, add dynamic ranks

1. use ManagedPtr instead of a Tensor in backend wrapper
2. add new methods to tensor classes
  - size_range: computes the combined size of for a given axis range
  - tensor span/view can be constructed from a raw pointer and shape
3. the tensor classes can change their rank at runtime (previously rank was fixed at compile-time)
4. remove device code from tensor classes (as they are unused)
5. enforce strict conditions on tensor class APIs to improve debugging ability

* fix parametric relu activation

* add squeeze/unsqueeze tensor API

* add reorg layer

* optimize permute and enable 2d permute

* enable 1d and 2d slice

* add split layer

* add shuffle channel layer

* allow tensors of different ranks in reshape primitive

* patch SliceOp to allow Crop Layer

* allow extra shape inputs in reshape layer

* use `std::move_backward` instead of `std::move` for insert in resizable_static_array

* improve workspace management

* add spatial LRN

* add nms (cpu) to region layer

* add max pooling with argmax ( and a fix to limits.hpp)

* add max unpooling layer

* rename DNN_TARGET_CUDA_FP32 to DNN_TARGET_CUDA

* update supportBackend to be more rigorous

* remove stray include from preventing non-cuda build

* include op_cuda.hpp outside condition #if

* refactoring, fixes and many optimizations

* drop DNN_TARGET_CUDA_FP64

* fix gcc errors

* increase max. tensor rank limit to six

* add Interp layer

* drop custom layers; use BackendNode

* vectorize activation kernels

* fixes for gcc

* remove wrong assertion

* fix broken assertion in unpooling primitive

* fix build errors in non-CUDA build

* completely remove workspace from public API

* fix permute layer

* enable accuracy and perf. tests for DNN_TARGET_CUDA

* add asynchronous forward

* vectorize eltwise ops

* vectorize fill kernel

* fixes for gcc

* remove CSL headers from public API

* remove csl header source group from cmake

* update min. cudnn version in cmake

* add numerically stable FP32 log1pexp

* refactor code

* add FP16 specialization to cudnn based tensor addition

* vectorize scale1 and bias1 + minor refactoring

* fix doxygen build

* fix invalid alignment assertion

* clear backend wrappers before allocateLayers

* ignore memory lock failures

* do not allocate internal blobs

* integrate NVTX

* add numerically stable half precision log1pexp

* fix indentation, following coding style,  improve docs

* remove accidental modification of IE code

* Revert "add asynchronous forward"

This reverts commit 1154b9da9da07e9b52f8a81bdcea48cf31c56f70.

* [cmake] throw error for unsupported CC versions

* fix rebase issues

* add more docs, refactor code, fix bugs

* minor refactoring and fixes

* resolve warnings/errors from clang

* remove haveCUDA() checks from supportBackend()

* remove NVTX integration

* changes based on review comments

* avoid exception when no CUDA device is present

* add color code for CUDA in Net::dump
 2019-10-21 14:28:00 +03:00
Alexander Alekhin
e2a5a6a05c Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-09-25 18:32:44 +00:00
Lubov Batanina
e923712d81 Merge pull request #15572 from l-bat:deconv3d 
Fix computation of internal shapes in Deconvolution layer

* Fix computation of internal shapes

* Refactoring
 2019-09-25 15:35:04 +03:00