Nnstreamer Versions Save

:twisted_rightwards_arrows: Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.

v2.4.1

2 weeks ago

Pre-release for Tizen 9.0 : Tizen 9.0 M1 release (sync to Tizen 7.0 and 8.0)

  • nnstreamer v2.4.1
  • nnstreamer-edge v0.2.5
  • ml-api v1.8.5
  • mlops-agent v1.8.5

v2.0.1

2 years ago

This is a LTS release 2.0.1, including bugfixes for 2.0 LTS release.

What's Changed

Full Changelog: https://github.com/nnstreamer/nnstreamer/compare/v2.0.0...v2.0.1

v2.1.1

2 years ago

2.1.0 -> 2.1.1 - Tizen 7.0 M1 RCx preparation and NNStreamer Mini Summit 2022-04 release.

    - NNStreamer-Edge refactoring (module for Among-Device AI (a.k.a. Edge-AI))
            - Ongoing effort of nnstreamer-edge separation from nnstreamer.
            - In the future, nnstreamer-edge will provide among-device AI functions and nnstreamer will provide gstreamer plugins for such functions. Non-gstreamer systems may connect to nnstreamer-edge based pipelines without gstreamer as clients.
            - NNStreamer-Edge will be using AITT as its default backend, leaving protocol issues to AITT.
            - In the future, nnstreamer-edge will be compatible with non-Linux ultra-lightweight systems (e.g., Tizen-RT)

    - ML-Service API preparation is going on at api.git.

    - Major features
            - MQTT timestamping w/ NTP. (later will be migrated to nnstreamer-edge & aitt)
            - Query (later will be migrated to nnstreamer-edge & aitt): robustness support, mqtt-hybrid protocol, performance fixes for multi-clients.
            - More coverage for SNPE support: quantized model support, SNPE dimension bug workaround, fixes from/for production team.
            - Flexible tensor support w/ decoder, converter, flatbuffer.

    - Minor features
            - MQTT unittest basis, generic stream support, android support, timeout handling, ... (and many!)
            - Utility functions exported for plugin writers.
            - Tensorflow-lite delegation refactored for generality: may use XNNPACK more easily.
            - Tensorflow-lite multi-lib support.
            - PyTorch: support complex output tensor formats.
            - NNStreamer multi-lib support.
            - Decoder: boundingbox-yolov5
            - Filter: TRIx-Engine support. (NPUs of Samsung 2022 TV)
            - Docker support refactored and cleaned up.

    - Fixes
            - ARMNN build errors.
            - Android errors
            - Build errors with recent compiler updates. (gcc 11)
            - Fixes upstreamed from productions
            - Errors w/ library updates: Lua >= 5.3, GLib >= 2.68
            - Regression fixes: openvino, edgetpu, tensorrt
            - Memory leaks in C++ subplugin infra.

    - Known issues: PPA/Launchpad build broken!

2.0.0 -> 2.1.0 - 2.1.0 is a devel version for 2.2.0 release, which is planned to be the LTS release of 2022.

What's Changed

New Contributors

Full Changelog: https://github.com/nnstreamer/nnstreamer/compare/v2.0.0...v2.1.1

v2.0.0

2 years ago

This is the LTS release of 2022, version 2.0.0.

The key features of 2.0 release include:

  • The first release with edge-AI (among-device AI) elements.
  • Stream data types are expanded to support flexible tensors (for schema-less streams) and sparse tensors.
    • The original stream type, other/tensor''' (single tensor), will be obsoleted. Please use other/tensors''' with ```num_tensors=1''' instead.
  • A few more hardware accelerators and neural network frameworks are adopted.

For more information, please refer to https://github.com/nnstreamer/nnstreamer/wiki/Release-Note-v2.0.0

v1.7.2

2 years ago

1.7.2 is the second devel-unstable release for 1.8 RC. Note that 1.7.1+a is released with Tizen 6.5 M1.

1.7.1 -> 1.7.2 (includes a huge amount of changes)

        - NNStreamer for Edge-AI project started.
                - Main festures of 1.8.0 release and its immediate successors will be "Edge-AI", which allows distributed on-device AI inferences.

                - The new stream type, "Flex-Tensor", is introduced. Dimensions and types of tensor stream may vary per frame without cap-renegotiations.
                        - Many nnstreamer's tensor-* elements support Flex-Tensor.
                        - You may use tensor-converter to convert between flex-tensor and (static) tensor.
                - MQTT-SINK and MQTT-SRC elements are added for edge-AI systems with MQTT pub/sub streams.
                        - MQTT streams support "ANY" capabilities.
                        - Assuming that clocks of nodes are synchronized by NTP or other mechanisms, pipeline users may send timestamp related info via MQTT streams for multi-source synchronization.
                - Tensor-crop, a new nnstreamer-gstreamer element.
                        - Basic feature only (cropping a tensor stream with information of another tensor stream)

        - Major features
                - GSTPipeline to PBTXT parser. You can use PBTXT-pipeline visualization tools with the parsed results.
                - FlexBuffers support.
                - TVM support

                - Tensor-IF with custom (user code plugged at run-time) conditions
                - Tensorflow-lite delegation designation is generalized.
                - Tensorflow2-lite XNNPACK delegation
                - NNTrainer-inference can be attached as a filter along with both API sets.
                - CAPI: updated documentation, added new enums for recent nnstreamer features, ...
                - API interface and implementation is separated to another git repository for better architecture.
                - Tensor-converter and Tensor-decoder support custom ops.
        - Minor features
                - Filter subplugin priority with ini file configuration.
                - Decoder/Bounding-Box improved: output tensor mapping, clamp bounding box locations, labeling issues, more options.
                - Decoder/Pose-Estimation improved: proper labeling.
                - Testcases added for gRPC, Android, Tensor-rate, ...
                - Refactoring (reduce complexity, remove duplicity, build options, ...)
                - Android build & release upgraded.
                - Converter usability upgrade: property to list subplugins, subplugin naming/install rules.
                - Pytorch: exception handling, Android build
                - gRPC: per-IDL packaging, interface updates, common-code revise, async mode, ...
                - Support Tensorflow 2.4 API (TF has broken backward compatibility again)
                - Tensor-transform: may operate on chosen tensor or channel only.
        - Fixes
                - Android resource leak.
                - CAPI timing, header issues, seg-faults, memory leaks, ...
                - MacOS build errors.
                - TensorRT dependency bugs
                - Edge-TPU compatibility issues.
                - Unit test fixes (memory leaks, resource leaks, skip disabled features, ...)
                - Fixed reported issues (security, memory leaks, query-caps, ...)
        - Extra
                - Support for Python 2.x is dropped.
                - Automated doc-page generation with Hotdoc.
                - Android build now includes GST-Shark for performance profiling.

v1.7.1

3 years ago

1.7.1 is the first devel-unstable release after 1.6.0 LTS release.

1.7.0 -> 1.7.1
        - Major features
                - Tensor-IF, a new element. It allows to create conditional branches based on tensor values.
                - Join, a new element. It merges output sinks from src pads of different elements with the same GST-Cap.
                - Tensor-rate, a new element. It allows throttling by generating QoS messages.
                - TensorRT support
                - TF1-lite and TF2-lite coexistance
                - TFx-lite NNAPI, GPU Delegation

        - Minor features
                - hw-accel options for tensor-filters are refactored
                - python3-embed enabled if python3 >= 3.8
                - Subplugin initialization optimization.
                - Docker scripts for Ubuntu developers.

        - Fixes
                - flatbuf dependency related with tensorflow-lite.
                - tensor-decoder configures framerate.
                - Dynamic dimension related API issues fixed.
                - MacOS, Yocto compatibility issues fixed. (A few Yocto known issues are still remaining.)
                - License mismatches resolved.
                - A few Test cases fixed.
                - Packaging issues fixed and style cleaned-up.

        - Extra
                - A lot of interesting sample applications are added.

v1.6.0

3 years ago

Linux Foundation AI Announcement

NNStreamer 1.6.0 is the next LTS version.

NNStreamer 1.6.0 targets Tizen 6.0 M2 release and next-year Android products.

Release Note of NNStreamer 1.6.0

We will attach binary packages as soon as CD system publishes them.

v1.0.1

4 years ago

For Tizen 5.5 Mx long-term stable maintance, we release NNStreamer 1.0.y LTS v1.0.1. Commits for 1.0.y LTS is managed in review.tizen.org (tizen_5.5 branch) and will be mirrored back to github.com/nnstreamer/nnstreamer.

In 1.0.y series, we will add critical hotfixes for 1.0 and additional requirements for Tizen 5.5 Mx only.

Changes from 1.0.0 to 1.0.1

  • All patches from 1.0.0 to 1.2.0 that were merged before 2019/10/14 (6cd9067d), the last master commit before Tizen 5.5 M2 release.
  • Allow non-tensor inputs with Pipeline's appsrc
  • nnfw (Neural Network Runtime of Tizen) integration
  • Bugfixes requested by quality assurance team for Tizen 5.5 releases
  • [HOTFIX] Duplicated free with appsrc/do-not-free-mode. (workaround)

RPM binaries are from download.tizen.org (reference build of Tizen 5.5 M3)

v1.4.0

4 years ago

1.3.1 -> 1.4.0

  • Stable release with API changes
  • Tensor-filter subplugin API has been updated.
  • Stability fixes & added unit test cases
  • C-API updates

1.3.0 -> 1.3.1 (1.4 RC2)

  • 1.3.1 is a devel version for 1.4.0 release.
  • Support C++ class custom filters. (C++ class as a NN model)
  • A tensor-filter instance may have multiple model files easily.
  • Updated env-var handling logic for non-Tizen devices.
  • Unit test: higher visibility & behavior correctness fixes.
  • Auto-generated test cases for tensor-filter sub-plugins (extensions).
  • Android/Java support with more convinient methods.
  • Support gcc9
  • Support openVino as a tensor-filter, allowing to accelerate with Intel NCS/Myriad.
  • Support NCSDK as a tensor-filter.
  • Support ARMNN as a tensor-filter. (support TF-Lite and Caffe models)
  • Reduce asserts and add error handling routines.
  • Support Androdi/SNAP as a tensor-filter.
  • Support hardware accelerators & 8-bit quantization for NNFW-Runtime & stabilize NNFW-Runtime support with test cases.
  • Support Edge-TPU and its runtime as a tensor-filter.
  • Filter subplugins refactored to have a single source file (.cc)
  • Support model reload
  • A lot of fixes for bugs found by Coverity, SVACE, and other static analysis tools

1.2.0->1.3.0 (1.4 RC1)

  • Development releases started.

v1.3.0

4 years ago

Release of NNStreamer 1.3.0

1.3.0 (odd-mid-version) is a development version.