Commit Graph

332 Commits

Author SHA1 Message Date
Yuantao Feng
b94e13c8ae
Merge pull request #23319 from fengyuentau:fix_zoo_issue_136
Related issue: https://github.com/opencv/opencv_zoo/issues/136

Features added:

- Support operators with multiple output: ONNX Split.
- Support Slice without steps.

Bugs fixed:

- Wrong settings in ClipByValue (Relu6).
- Wrong calculation of pads in convolution layer (It is wrong generally but only fixed specifically for CANN for now).

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-03-13 21:46:33 +03:00
Dmitry Kurtaev
76350cd30f
Merge pull request #23161 from dkurt:dnn_tflite
TFLite models importer

* initial commit

* Refactor TFLiteImporter

* Better FlatBuffers detection

* Add permute before 4D->3D reshape

* Track layers layout

* TFLite Convolution2DTransposeBias layer

* Skip TFLite tests without FlatBuffers

* Fix check of FlatBuffers in tests. Add readNetFromTFLite from buffer

* TFLite Max Unpooling test

* Add skip for TFLite unpooling test

* Revert DW convolution workaround

* Fix ObjC bindings

* Better errors handling

* Regenerate TFLite schema using flatc

* dnn(tflite): more checks, better logging

* Checks for unimplemented fusion. Fix tests
2023-02-13 14:00:20 +00:00
Yuantao Feng
c2b7c1f13b
Merge pull request #23219 from fengyuentau:add_gelu
Add GELU layer for vision transformers

* add gelu and gelu approximation

* drop setKernelParams
2023-02-10 18:03:29 +00:00
Alexander Alekhin
96a45e842e
Merge pull request #23061 from WanliZhong:gemm_cuda
DNN: make GEMM can be supported with transA and transB in CUDA
2023-02-09 00:06:32 +03:00
wanli
4718a4bf81 make GEMM can be supported with transA and transB in CUDA 2023-01-31 15:14:17 +08:00
Yuantao Feng
4d918ba40b
Merge pull request #23047 from fengyuentau:layer_norm
dnn: add layer normalization for vision transformers

* add layer norm onnx parser, impl and tests

* add onnx graph simplifier for layer norm expanded

* handle the case when constants are of type Initializer

* add test case for layer norm expanded with initializers

* use CV_Assert & CV_CheckType in place of CV_Assert_N; use forward_fallback for OCL_FP16

* use const ref / ref in parameters of invoker::run; extract inner const if from nested loop; use size_t in place of ull

* template hasBias

* remove trailing whitespace

* use pointer parameter with null check; move normSize division & mean_square division outside of loop; use std::max to ensure positive value before std::sqrt

* refactor implementation, optimize parallel_for

* disable layer norm expanded

* remove the removal of layer norm optional outputs
2023-01-27 16:35:59 +03:00
Alexander Alekhin
b42c11de82 pre: OpenCV 4.7.0 (version++) 2022-12-25 17:00:22 +00:00
Yuantao Feng
a2b3acfc6e
dnn: add the CANN backend (#22634)
* cann backend impl v1

* cann backend impl v2: use opencv parsers to build models for cann

* adjust fc according to the new transA and transB

* put cann net in cann backend node and reuse forwardLayer

* use fork() to create a child process and compile cann model

* remove legacy code

* remove debug code

* fall bcak to CPU backend if there is one layer not supoorted by CANN backend

* fix netInput forward
2022-12-21 09:04:41 +03:00
Alexander Smorkalov
e14ca39fd7
Merge pull request #22857 from fengyuentau:batched_nms
dnn: add batched nms
2022-11-30 12:37:49 +03:00
fengyuentau
9fded9ca53 batched nms impl 2022-11-29 15:32:34 +08:00
fengyuentau
441624a5fb tile impl 2022-11-29 11:15:38 +08:00
Zihao Mu
903bf0147e
Merge pull request #22666 from zihaomu:support_onnx_qdq_model
DNN: let Quant and Dequant of ONNX_importer support the Constant input.

* let Quant and Dequant support the Constant input.

* fix negative value of axis.
2022-10-31 16:06:31 +00:00
Alexander Smorkalov
ec7fc5adca
Merge pull request #22529 from fengyuentau:scatter_scatternd
DNN: supports Scatter and ScatterND from ONNX
2022-10-17 14:57:46 +03:00
fengyuentau
d24d8f2abe implementation of scatter and scatternd with conformance tests enabled 2022-10-17 11:30:32 +08:00
Alexander Alekhin
762481411d Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2022-10-15 16:44:47 +00:00
Zihao Mu
1e2ceca4df add enableWinograd API for Net. 2022-10-09 09:33:07 +08:00
Alexander Alekhin
347246901e Merge pull request #21745 from alalek:dnn_plugin_openvino 2022-10-08 22:32:25 +00:00
Alexander Alekhin
43b2bb2c25 dnn: plugin support for OpenVINO 2022-10-07 16:57:31 +00:00
Voron
cbf43a54fb added opencv for openvino tutorial 2022-09-28 12:05:28 +02:00
Egor Smirnov
65f71ce2eb add Gather implementation 2022-09-19 15:06:44 +03:00
Alexander Alekhin
65bdb3a544 dnn: eliminate GCC12 warning in total() call 2022-09-14 11:37:00 +00:00
Alexander Alekhin
ca7f964104 dnn: use inheritance for OpenVINO net impl 2022-09-06 18:05:00 +00:00
Zihao Mu
bb64db98d8
Further optimization of Conv2D, fused Conv_Add_Activation, bring latest code from ficus OpConv.fx. (#22401) 2022-08-26 12:57:25 +03:00
Alexander Smorkalov
bb71cb200e
Merge pull request #22199 from zihaomu:bug_fix_22195
DNN: Reduce Layer (add dynamic batch and ReduceSum support)
2022-08-11 12:59:51 +03:00
Zihao Mu
d4640f4647 support ReduceLayer without reshape layer. 2022-08-02 10:32:31 +08:00
rogday
ed69bcae2d
Merge pull request #21865 from rogday:nary_eltwise_layers
Reimplementation of Element-wise layers with broadcasting support

* init

* semi-working initial version

* add small_vector

* wip

* remove smallvec

* add nary function

* replace auto with Mat in lambda expr used in transform

* uncomment asserts

* autobuffer shape_buf & step_buf

* fix a missing bracket

* fixed a missing addLayer in parseElementWise

* solve one-dimensional broadcast

* remove pre_broadcast_transform for the case of two constants; fix missing constBlobsExtraInfo when addConstant is called

* one autobuffer for step & shape

* temporal fix for the missing original dimension information

* fix parseUnsqueeze when it gets a 1d tensor constant

* support sum/mean/min/max with only one input

* reuse old code to handle cases of two non-constant inputs

* add condition to handle div & mul of two non-constant inputs

* use || instead of or

* remove trainling spaces

* enlarge buf in binary_forward to contain other buffer

* use autobuffer in nary_forward

* generate data randomly and add more cases for perf

* add op and, or & xor

* update perf_dnn

* remove some comments

* remove legacy; add two ONNX conformance tests in filter

* move from cpu_denylist to all_denylist

* adjust parsing for inputs>=2

Co-authored-by: fengyuentau <yuantao.feng@opencv.org.cn>
2022-07-19 06:14:05 +03:00
Zihao Mu
a80fcacd90
Merge pull request #21372 from zihaomu:dnn_quantize_per_tensor
Add per_tensor_quantize to int8 quantize

* add per_tensor_quantize to dnn int8 module.

* change api flag from perTensor to perChannel, and recognize quantize type and onnx importer.

* change the default to hpp
2022-07-05 19:14:42 +03:00
Alexander Alekhin
e9428726ca pre: OpenCV 4.6.0 (version++) 2022-05-23 19:25:16 +00:00
Alexander Alekhin
400906b433 pre: OpenCV 3.4.18 (version++) 2022-05-23 19:18:02 +00:00
zihaomu
e36948cfbc add ONNX OP sign, shrink and reciprocal 2022-04-07 15:32:12 +08:00
Zihao Mu
7b582b71ba
Merge pull request #21036 from fengyuentau:timvx_backend_support
dnn: TIM-VX NPU backend support

* Add TimVX NPU backend for DNN module.

* use official branch from tim-vx repo; fix detecting viv sdk

Co-authored-by: fytao <yuantao.feng@outlook.com>
2022-03-31 21:42:11 +00:00
Alexander Alekhin
c9b90884da Merge pull request #21601 from zihaomu:add_reduceLayer 2022-03-26 10:20:10 +00:00
luz paz
8e8e4bbabc dnn: fix various dnn related typos
Fixes source comments and documentation related to dnn code.
2022-03-23 18:12:12 -04:00
Zihao Mu
b6b5c27cec Support for some reduce layers for onnx 2022-03-18 10:19:13 +08:00
Tsukasa Sugiura
8db7d435b9
Merge pull request #21692 from UnaNancyOwen:add_softmax
* add apply softmax option to ClassificationModel

* remove default arguments of ClassificationModel::setSoftMax()

* fix build for python

* fix docs warning for setSoftMax()

* add impl for ClassficationModel()

* fix failed build for docs by trailing whitespace

* move to implement classify() to ClassificationModel_Impl

* move to implement softmax() to ClassificationModel_Impl

* remove softmax from public method in ClassificationModel
2022-03-07 20:26:15 +00:00
Alexander Alekhin
19926e2979 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2022-02-11 17:32:37 +00:00
Alexander Alekhin
effce0573b dnn: drop legacy Inference Engine NN builder API 2022-02-10 11:55:24 +00:00
Alexander Alekhin
57d3002ee1 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2022-02-06 16:10:43 +00:00
Alexander Alekhin
67978b5746 dnn(ngraph): add debuging messages 2022-02-06 13:08:53 +00:00
Alexander Alekhin
d573472a86 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2022-01-31 12:53:45 +00:00
Alexander Alekhin
85719a0a5d dnn: support outputs registration under new names
- fixed ONNX importer
2022-01-29 23:29:51 +00:00
Alexander Alekhin
b796ededae Merge pull request #21437 from alalek:dnn_api_explicit_const_4.x 2022-01-21 20:19:50 +00:00
Alexander Alekhin
eb7b45d26b dnn: fix API - explicit ctors, const methods 2022-01-21 12:38:51 +00:00
rogday
0fe7420638 fix model diagnostic tool 2022-01-18 01:22:22 +03:00
Alexander Alekhin
b304730225 dnn: fix API - explicit ctors, const methods 2022-01-17 21:45:29 +00:00
Alexander Alekhin
172c539a5a Merge pull request #21281 from alalek:update_version_4.5.5-pre 2021-12-18 13:46:38 +00:00
Smirnov Egor
71a22e45b0 add celu, hardsigmoid, selu, thresholdedrelu layers 2021-12-18 03:19:54 +03:00
Smirnov Egor
1bd382c1d0 Add acos, acosh, asin, asinh, atan, atanh, cos, cosh, erf, hardswish, sin, sinh, softplus, softsign, tan layers 2021-12-17 18:19:40 +03:00
Alexander Alekhin
07dca8cc03 pre: OpenCV 4.5.5 (version++) 2021-12-17 10:12:11 +00:00
Alexander Alekhin
60c093f086 pre: OpenCV 3.4.17 (version++) 2021-12-17 10:05:52 +00:00