Update OpenVINO to 2025.4 ver #493
Open
+34
−34
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
tbujewsk
requested review from
BaoHuiling,
OskarFiedot,
ZiningLi,
dmichalo,
jmotow,
marcin-wadolkowski,
mholowni,
msmiatac,
nszczygl9,
pbartosik,
qianlongding,
yangjianfeng1208 and
yunowo
as code owners
msmiatac
approved these changes
Dec 30, 2025
fleaxin
pushed a commit
to fleaxin/dlstreamer
that referenced
this pull request
Jan 1, 2026
…-edge-platform#472) * initial skeleton (open-edge-platform#1) * initial skeleton * rename evam to dlstreamer-pipeline-server * Deep Learning Streamer v2025.0.1 (open-edge-platform#8) * Deep Learning Streamer v2025.0.1 Co-authored-by: Tomasz Janczak <tomasz.janczak@intel.com> Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> Co-authored-by: Jaroslaw Motowidlo <jaroslaw.motowidlo@intel.com> Co-authored-by: Natalia Szczyglo <natalia.szczyglo@intel.com Co-authored-by: Marcin Wadolkowski <marcin.wadolkowski@intel.com> Co-authored-by: Maciej Smiatacz <maciej.smiatacz@intel.com> Co-authored-by: Oskar Fiedot <oskar.fiedot@intel.com> Co-authored-by: Dawid Michalowski <dawid.michalowski@intel.com> * Update of README and RELEASE_NOTES * Update of RELEASE_NOTES --------- Co-authored-by: Dawid Michalowski <dawid.michalowski@intel.com> * Deep Learning Streamer v2025.0.1.2 (open-edge-platform#35) * Deep Learning Streamer v2025.0.1.2 * Add spdlog as a submodule at DLStreamer v2025.0.1.2 * Update RELEASE_NOTES.md for DLStreamer 2025.0.1.2 (open-edge-platform#36) * Modify DLS_install_prerequisites.sh, download_public_models.sh and hello_dlstreamer.sh (open-edge-platform#57) * Add Dockerfiles and modify requirements.txt (open-edge-platform#59) * Required changes for DLStreamer v2025.0.1.3 release (open-edge-platform#66) * Add Dockerfiles and modify requirements.txt * required hanges for dlstreamer 2023.0.1.3 release * Update DLStreamer versioning style (open-edge-platform#80) * Update DLStreamer versioning style * Fix typo in dev-ubuntu24 Dockerfile (open-edge-platform#81) * Porting DLStreamer docs content (open-edge-platform#98) * Update RELEASE_NOTES.md Release 2025.0.1.3 (open-edge-platform#100) * Update DLStreamer README about additional sections. (open-edge-platform#111) * [DLStreamer] Add link to installed packages (open-edge-platform#117) * [DLStreamer] Script and Dockerfiles for building .deb packages (open-edge-platform#119) * [DLStreamer] Update install documentation (open-edge-platform#124) * enable build within the Intel network (open-edge-platform#125) * [DL Streamer] Add help messages to scripts and modify hello_dlstreamer arguments (open-edge-platform#127) * [DL Streamer] Fix build_deb_packages.sh script. (open-edge-platform#149) * [DLStreamer] Align DL Streamer code with the internal repository (open-edge-platform#152) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Fix PYTHONPATH for gstgva module (open-edge-platform#155) Co-authored-by: Dawid Michalowski <dawid.michalowski@intel.com> * [DLStreamer] Update installation procedure when building from sources. (open-edge-platform#165) * [DLStreamer] Update spdlog to v1.15.3 (open-edge-platform#166) * [DLStreamer] Reorganization of workflows - one main per PR, two per PR sub-workflows (dev_img and deb_pkg+bin_img), weekly Docker img build (open-edge-platform#157) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> Co-authored-by: Dawid Michalowski <dawid.michalowski@intel.com> * [DLStreamer] Fix memory leak when detection output is augmented. (open-edge-platform#172) * [DLStreamer] Fix broken links in documentations (#175) * [DLStreamer] New CI workflow for building DL Streamer documentation (open-edge-platform#176) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Added gvaattachroi element (open-edge-platform#186) * [DLStreamer] Add support for building DLStreamer on Fedora 41 (open-edge-platform#187) * [DLStreamer] Optimize Docker images building time using cache solutions. (open-edge-platform#188) * [DLStreamer] Bump setuptools version. (open-edge-platform#191) * [DLStreamer] Update gvametaaggregate element description (open-edge-platform#190) * [DLStreamer] Fix pip command in readme (open-edge-platform#198) * [DLStreamer] New script for DLS environment configuration (open-edge-platform#205) * [ITEP-26367] Add PaddleOCR (LPR) converter (open-edge-platform#199) Co-authored-by: Tomasz Janczak <Tomasz.Janczak@intel.com> * [DLStreamer] Documentation - remove GPU drivers installation steps in advanced_installation/prereq (open-edge-platform#213) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Add functional tests - sample tests on TGL and ARL, on-host and Docker (open-edge-platform#206) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] BlobToTensorConverter implementation refactoring (open-edge-platform#221) * [DLSTREAMER] Fix code style in PaddleOCR converter (open-edge-platform#217) * [DLStreamer] Add Paddle OCR to download_public_models.sh (open-edge-platform#219) Co-authored-by: Tomasz Janczak <Tomasz.Janczak@intel.com> Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [SCANS] Add Trivy config scan (open-edge-platform#241) * [DLStreamer] Apply VA_PROC_PIPELINE_FAST settings for fast scaling mode (open-edge-platform#244) * [DLStreamer] modified source files to avoid compilation problems on W… (open-edge-platform#245) * [DLStreamer] Add more excluded dirs to .dockerignore (open-edge-platform#246) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Add license plate detector to download_public_models.sh (open-edge-platform#249) * [DLSTREAMER] Prevent Paddle OCR errors in special cases (open-edge-platform#250) * [DLSTREAMER] Add license plate recognition sample (open-edge-platform#251) * [DLStreamer] Modify DLS_install_prerequisites.sh (open-edge-platform#258) * [DLStreamer] modified source files to avoid compilation problems on W… (open-edge-platform#259) * [DLStreamer] Minor LPR documentation update (open-edge-platform#261) * [DLStreamer] Add Dockerfile for rpm package build (open-edge-platform#267) - Add Dockerfile for rpm package build - Add test dockerfile template for fedora rpm package - Add fedora support to hello_dlstreamer.sh script - Adjust the setup_dls_env.sh script - Change path /home/$USER to $HOME - Add /usr/local/lib path to LD_LIBRARY_PATH where it's missing * [DLStreamer] Lpr vaapi (open-edge-platform#271) * [DLSTREAMER] Add LPR models to documentation (open-edge-platform#272) * [DLStreamer] Download models modifications (open-edge-platform#273) * [DLStreamer] Add anomaly-detection support (open-edge-platform#279) * [DLStreamer] Remove fixed value of MODELS_PATH from hello_dlstreamer.sh (open-edge-platform#281) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] fix sporadic memory errors in GStreamer's analytics library (open-edge-platform#282) * [DLStreamer] Cumulative merge of the pre-Windows enabling changes (open-edge-platform#283) * [DLStreamer] Remove special case for LVM models. (open-edge-platform#278) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Warn users if a model was quantized with different runtime version (open-edge-platform#293) * [DLStreamer] changes needed for compilation and linking on Windows (open-edge-platform#299) * [DLStreamer] Minor fixes to anomaly-detection sample tutorial (open-edge-platform#312) * [DLStreamer] Replace GValueArray with GST_TYPE_ARRAY; fix mem leak in yolo-pose (open-edge-platform#309) * [DLStreamer] Functional tests - preparing samples testing workflow (open-edge-platform#314) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Align OpenVINO version to 2025.1.0 and change default Docker build to Release (open-edge-platform#326) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Use tensor wrappers in yolo converter. (open-edge-platform#322) * [DLStreamer] YOLO detection model quantization (open-edge-platform#323) * [DLStreamer] Next portion of compilation and linking changes specific to Windows (open-edge-platform#338) * [DLStreamer] Add option to schedule incoming frames according to their presentation time (open-edge-platform#375) * [SCANS][DLStreamer] Add codeql c++ scanning for DLStreamer and python/actions scanning for all. (open-edge-platform#348) * [DLStreamer] Improve documentation building and checking (open-edge-platform#384) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Updated samples to support new INT8 models (open-edge-platform#406) * [DLStreamer] changes needed for compilation and linking on Windows (open-edge-platform#376) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Enable models downloading workflow (open-edge-platform#404) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DL Streamer] Create multistage Ubuntu24/22 dockerfiles (open-edge-platform#392) Co-authored-by: nszczygl9 <118973656+nszczygl9@users.noreply.github.com> * [DLStreamer] Next portion of the changes to enable compilation on Windows (open-edge-platform#417) * [DLStreamer] Improve YOLO sample exit codes (open-edge-platform#418) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Fixes in download_public_models - Ultralytics fixed 8.3.153 version, quantization excluding and venvs cleaning (open-edge-platform#440) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Add missing models for Unit Tests (open-edge-platform#461) * [DLStreamer] Enable functional samples tests for pull request workflow CI (open-edge-platform#426) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Added Windows Dockerfile, setup script for Windows, fixe… (open-edge-platform#460) * [DLStreamer] modified instance segmentation script (open-edge-platform#467) * [DLStreamer] Add DeepScenario support (open-edge-platform#465) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Reduce ubuntu 22/24 image size (open-edge-platform#462) Co-authored-by: nszczygl9 <118973656+nszczygl9@users.noreply.github.com> Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Modify models downloading worfklows. (open-edge-platform#481) * [DLStreamer] Enable Unit Tests -part1 (open-edge-platform#480) Co-authored-by: Michal Holownia <michal.holownia@intel.com> * [DLStreamer] Minor refactoring in detection_anomaly converter (open-edge-platform#484) * [DLStreamer] Fix Windows dockerfile - escape (open-edge-platform#492) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Fix metaconvert unit test (open-edge-platform#493) * [DLStreamer] Update to OpenVino 2025.2 ver (open-edge-platform#495) * [DLStreamer] Create multistage Fedora41 dockerfile (open-edge-platform#477) * [DLStreamer] Add support for custom post-processing converters (open-edge-platform#501) * [DLStreamer] Makefile added with common targets (#517) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Fix fedora dockerfile trivy scan (#512) * [DLStreamer] Add guide for opencv removal (#514) Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> * [DLStreamer] Unit tests fixes (#523) * [DLStreamer] Fix gstreamer build error in manual compilation - update docs (#522) * [DLStreamer] Update dockerfiles (#544) * [DLStreamer] Modify NPU drivers installation. (#562) * Enable command-line overrides of pre-processing parameters in model.xml runtime section. (#574) * [DLStreamer] Add samples for custom post-processing library (#571) * [DLStreamer] Update NPU driver version (#584) * [DLStreamer] Fix downloading public models script to work inside container (#586) * [DLStreamer] Add support for Clip-ViT-Base-B16/B32 with va-surface-sharing backend (#576) * [DLStreamer] Read optimal batch size from OV device instead of hardcoded heuristics. (#591) * [DLStreamer] Windows adjustments for CI integration + new build_dlstreamer_dlls.ps1 script (#590) Signed-off-by: dmichalo <dawid.michalowski@intel.com> Co-authored-by: Marcin Wadolkowski <marcin.wadolkowski@intel.com> * [DLStreamer] Update GStreamer and gst-plugins-rs to 1.26.4 (#604) * [DLStreamer] Improve VA context reuse (#608) * [DLStreamer] Add OpenVINO GenAI element to support MiniCPM (#599) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Fix apt installation guide (#545) Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> * [DLStreamer] Update groundtruth files for clips (#626) * [DLStreamer] Add examples for OBB and Segmentation in YOLO sample (#634) * [DLStreamer] Update license plate detection model and LPR sample (#681) * Make all git clone commands referring to v1.2.0 release branch (#656) * [DLStreamer] Replace unzip command with Python zipfile extraction in download_public_models.sh (#699) * [DLStreamer] Bump DL Streamer version to 2025.1.2 (#703) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Remove unused build_deb_packages.sh script (#712) Signed-off-by: dmichalo <dawid.michalowski@intel.com> * [DLStreamer] Add DOCKER_REGISTRY variable to ubuntu Dockerfiles. (#714) * [DLStreamer] Coverity fixes (#719) * [DLStreamer] [1.2.0] Update groundtruths for testcases and fix missing libopencv-dev (#730) * [DOCS] Translating DL Streamer docs to Markdown for release 1.2.0 (#750) * [DOCS] Translating DL Streamer docs from reST to Markdown for release 1.2.0 (#765) Co-authored-by: MikolajX Pytlik <mikolajx.pytlik@intel.com> * [DOCS] Installing DL Streamer on Windows - port to release 1.2.0 (#785) * [DLStreamer] Update docs. (#794) * [DOCS] Adding release notes for DL Streamer for 1.2.0 (#795) * [DOCS] Fixing elements list for 1.2.0 (#799) * [DOCS] Fixes for documentation build for DL Streamer (#801) * dl-streamer/docs: Added compilation steps for EMT OS (#788) Signed-off-by: Vinod K B <vinod.k.b@intel.com> Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com> Co-authored-by: mpytlik-intel <mikolajx.pytlik@intel.com> * [DOCS] Fixing issues for documentation build for 1.2.0 (#810) * [DOCS] Update references to release-1.2.0 (#745) Co-authored-by: Xintian Wu <75466671+xwu2intel@users.noreply.github.com> * [DOCS] Proofreading dlstreamer readme overview for 1.2.0 (#819) * [DOCS] Update dl streamer release notes for 1.2.0 (#841) * [DOCS] Proofreading Deep Learning Streamer Dev Guide - pass 1 (#836) * [DLStreamer] Fix docs. (#851) Co-authored-by: Bartosik, Pawel <pawel.bartosik@intel.com> Co-authored-by: dmichalo <dawid.michalowski@intel.com> * [DOCS] DL Streamer Elements content review - port to release-1.2.0 (#873) * [DOCS] Fix code highlighting issues (#876) * [DOCS] cpp interfaces table fix (#885) * libraries/dlstreamer/SPECS: Enabled DL Streamer RPM package to work on EMT (#879) This PR introduces RPM packaging infrastructure for Intel DL Streamer and its dependencies, enabling modular distribution of the framework through individual RPM packages. - RPM spec files for all major dependencies (paho-mqtt-c, ffmpeg, gstreamer, opencv) - Main intel-dlstreamer RPM package with development and samples subpackages - Build automation scripts for source downloading and package compilation Signed-off-by: Vinod K B <vinod.k.b@intel.com> * dl-streamer/SPECS: Updated the right DL streamer version (#893) Changes: 1. Fixed the DL Streamer version to 2025.1.2 2. Fixed issues in the download and spec files Signed-off-by: B, Vinod K <vinod.k.b@intel.com> * [DOCS] Fixing ref issues in build for DL Streamer docs (#932) * [DOCS] Proofreading Dev Guide in DL Streamer docs (#928) * DL-Streamer restore tab layout (#927) Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com> * [DOCS] Reformatting conf.py in DL Streamer docs (#970) * [DOCS] Fixing docs structure in dl streamer for release 1.2.0 (#988) * [DOCS] hide toctrees in markdown files (#992) * [DOCS] Hiding Sphinx directives from preview of Markdown files for release 1.2.0 (#994) * [DOCS] Content review - Get Started section of DL Streamer (#1003) * [DOCS] Hiding eval-rst and orphan Sphinx directives for release 1.2.0 (#1005) * [DOCS] Updating DL Streamer docs - name change (#1007) * Remove functional_tests --------- Signed-off-by: dmichalo <dawid.michalowski@intel.com> Signed-off-by: Vinod K B <vinod.k.b@intel.com> Signed-off-by: B, Vinod K <vinod.k.b@intel.com> Co-authored-by: Xintian Wu <75466671+xwu2intel@users.noreply.github.com> Co-authored-by: Tomasz Bujewski <tomasz.bujewski@intel.com> Co-authored-by: Dawid Michalowski <dawid.michalowski@intel.com> Co-authored-by: Tomasz Janczak <Tomasz.Janczak@intel.com> Co-authored-by: OskarFiedot <100859707+OskarFiedot@users.noreply.github.com> Co-authored-by: marcin-wadolkowski <106673332+marcin-wadolkowski@users.noreply.github.com> Co-authored-by: Michal Holownia <michal.holownia@intel.com> Co-authored-by: jmotow <jaroslaw.motowidlo@intel.com> Co-authored-by: msmiatac <153737147+msmiatac@users.noreply.github.com> Co-authored-by: pbartosik <pawelbrtsk@gmail.com> Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> Co-authored-by: Yun Liu <liuyun.97@gmail.com> Co-authored-by: Marcin Wadolkowski <marcin.wadolkowski@intel.com> Co-authored-by: Yun Liu <yun.m.liu@intel.com> Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com> Co-authored-by: MikolajX Pytlik <mikolajx.pytlik@intel.com> Co-authored-by: Vinod Kumar B <vinod.k.b@intel.com> Co-authored-by: Bartosik, Pawel <pawel.bartosik@intel.com>
fleaxin
pushed a commit
to fleaxin/dlstreamer
that referenced
this pull request
Jan 1, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.