Extended the Semantic Segmentation demo with new type of networks ( unet-camvid-onnx-0001): #20476.Added various graph-level optimizations to the MTCNN demo: #20383, #20474.Merged the first bits of the upcoming oneVPL integration for accelerated Media on Windows.Added serialization support for the cv::MediaFrame data structure: #20329.Added serialization support for graph constant data: #20372.Covered serialization-related methods with Doxygen documentation: #20163.Aligned the compileStreaming() behavior in Python with the C++ version: #20555.Extended OpenVINO™ inference backend parameters in Python with methods to configure constant input layers and the number of asynchronous infer requests: #20508.Fixed issue with possible extra external resources being held during the inference execution, causing hangs at some platforms (e.g.Fixed issues with incorrect precision and preprocessing options set for imported binary network blobs: #20528.Introduced FP16 data type support in the OpenVINO™ inference backend: #20490.Fixed cv::RMat and introduced cv::MediaFrame handling with the desync() operation: #20747.Fixed cv::RMat handling in the regular execution mode: #20593.Introduced a full-featured graph reshape support for the heterogeneous graphs: #20705.Introduced generic visitor(s) for the G-API's own implementation of variant data structure: #20039.added support for models with non-FP32 outputs or for outputs with 1D layout.added support for OpenVINO 2021.4.1 LTS release.Intel® Inference Engine backend ( OpenVINO™ ):
Implement CTC prefix beam search decode for TextRecognitionModel: #20524 Fixed several memory access issues in OpenCL kernels.Fixed convolution with asymmetric padding.Improved layers / activations / supported more models: Tutorial for Universal Intrinsics and parallel_for_ for efficient cross-platform algorithm implementation: #20361.Optimizing OpenCV DNN for RISC-V: #20287 + #20521.Improved OpenCV bindings for Julia: opencv_contib#3009.8-bit quantization in DNN Module: #20228 + onnx importer #20535.Here is the list of merged functionality: 11 projects are successful, and most of the results are already merged into OpenCV tree and available in 4.5.4 (in the main repository or in opencv_contrib). The fall update for OpenCV 4.x has been released.
0 kommentar(er)
