opencv

Open Source Computer Vision Library https://opencv.org/

Vadim Pisarevsky 3cd57ea09e Merge pull request #26056 from vpisarev:new_dnn_engine New dnn engine #26056 This is the 1st PR with the new engine; CI is green and PR is ready to be merged, I think. Merge together with https://github.com/opencv/opencv_contrib/pull/3794 --- Known limitations: * [solved] OpenVINO is temporarily disabled, but is probably easy to restore (it's not a deal breaker to merge this PR, I guess) * The new engine does not support any backends nor any targets except for the default CPU implementation. But it's possible to choose the old engine when loading a model, then all the functionality is available. * [Caffe patch is here: #26208] The new engine only supports ONNX. When a model is constructed manually or is loaded from a file of different format (.tf, .tflite, .caffe, .darknet), the old engine is used. * Even in the case of ONNX some layers are not supported by the new engine, such as all quantized layers (including DequantizeLinear, QuantizeLinear, QLinearConv etc.), LSTM, GRU, .... It's planned, of course, to have full support for ONNX by OpenCV 5.0 gold release. When a loaded model contains unsupported layers, we switch to the old engine automatically (at ONNX parsing time, not at `forward()` time). * Some layers , e.g. Expat, are only partially supported by the new engine. In the case of unsupported flavours it switches to the old engine automatically (at ONNX parsing time, not at `forward()` time). * 'Concat' graph optimization is disabled. The optimization eliminates Concat layer and instead makes the layers that generate tensors to be concatenated to write the outputs to the final destination. Of course, it's only possible when `axis=0` or `axis=N=1`. The optimization is not compatible with dynamic shapes since we need to know in advance where to store the tensors. Because some of the layer implementations have been modified to become more compatible with the new engine, the feature appears to be broken even when the old engine is used. * Some `dnn::Net` API is not available with the new engine. Also, shape inference may return false if some of the output or intermediate tensors' shapes cannot be inferred without running the model. Probably this can be fixed by a dummy run of the model with zero inputs. * Some overloads of `dnn::Net::getFLOPs()` and `dnn::Net::getMemoryConsumption()` are not exposed any longer in wrapper generators; but the most useful overloads are exposed (and checked by Java tests). * [in progress] A few Einsum tests related to empty shapes have been disabled due to crashes in the tests and in Einsum implementations. The code and the tests need to be repaired. * OpenCL implementation of Deconvolution is disabled. It's very bad and very slow anyway; need to be completely revised. * Deconvolution3D test is now skipped, because it was only supported by CUDA and OpenVINO backends, both of which are not supported by the new engine. * Some tests, such as FastNeuralStyle, checked that the in the case of CUDA backend there is no fallback to CPU. Currently all layers in the new engine are processed on CPU, so there are many fallbacks. The checks, therefore, have been temporarily disabled. --- - [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 - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake		5 months ago
.github	Added Ubuntu 24.04 pipeline for 5.x	8 months ago
3rdparty	Merge branch 4.x	5 months ago
apps	Merge branch '4.x' into '5.x'	8 months ago
cmake	Merge branch 4.x	5 months ago
doc	Merge pull request #25292 from kaingwade:features2d_parts_to_contrib	5 months ago
include	Move objdetect HaarCascadeClassifier and HOGDescriptor to contrib xobjdetect (#25198 )	12 months ago
modules	Merge pull request #26056 from vpisarev:new_dnn_engine	5 months ago
platforms	Merge pull request #26056 from vpisarev:new_dnn_engine	5 months ago
samples	Merge pull request #25292 from kaingwade:features2d_parts_to_contrib	5 months ago
.editorconfig	add .editorconfig	6 years ago
.gitattributes	cmake: generate and install ffmpeg-download.ps1	7 years ago
.gitignore	Merge pull request #17165 from komakai:objc-binding	5 years ago
CMakeLists.txt	Merge branch 4.x	5 months ago
CONTRIBUTING.md	migration: github.com/opencv/opencv	9 years ago
COPYRIGHT	Merge pull request #25520 from gursimarsingh:add-bigvision-copyright	6 months ago
LICENSE	Merge pull request #18073 from vpisarev:apache2_license	5 years ago
README.md	Merge branch 4.x	11 months ago
SECURITY.md	Updated PGP key for security reports	2 years ago

README.md

OpenCV: Open Source Computer Vision Library

Resources

Homepage: https://opencv.org
- Courses: https://opencv.org/courses
Docs: https://docs.opencv.org/5.x/
Q&A forum: https://forum.opencv.org
- previous forum (read only): http://answers.opencv.org
Issue tracking: https://github.com/opencv/opencv/issues
Additional OpenCV functionality: https://github.com/opencv/opencv_contrib
Donate to OpenCV: https://opencv.org/support/

Contributing

Please read the contribution guidelines before starting work on a pull request.

Summary of the guidelines:

One pull request per issue;
Choose the right base branch;
Include tests and documentation;
Clean up "oops" commits before submitting;
Follow the coding style guide.

Additional Resources

Submit your OpenCV-based project for inclusion in Community Friday on opencv.org
Subscribe to the OpenCV YouTube Channel featuring OpenCV Live, an hour-long streaming show
Follow OpenCV on LinkedIn for daily posts showing the state-of-the-art in computer vision & AI
Apply to be an OpenCV Volunteer to help organize events and online campaigns as well as amplify them
Follow OpenCV on Mastodon in the Fediverse
Follow OpenCV on Twitter
OpenCV.ai: Computer Vision and AI development services from the OpenCV team.