* Implement ROCm detectors
* Cleanup tensor input
* Fixup image creation
* Add support for yolonas in onnx
* Get build working with onnx
* Update docs and simplify config
* Remove unused imports
* Add support for yolonas in onnx
* Add correct deps
* Set ld library path
* Refactor cudnn to only be used in amd64
* Add onnx to docs and add explainer at the top
* Undo change
* Update comment
* Remove uneccesary
* Remove line change
* Initial support for Hailo-8L
Added file for Hailo-8L detector including dockerfile, h8l.mk, h8l.hcl, hailo8l.py, ci.yml and ssd_mobilenat_v1.hef as the inference network.
Added files to help with the installation of Hailo-8L dependences like generate_wheel_conf.py, requirements-wheel-h8l.txt and modified setup.py to try and work with any hardware.
Updated docs to reflect Initial Hailo-8L support including oject_detectors.md, hardware.md and installation.md.
* Update .github/workflows/ci.yml
typo h8l not arm64
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Update docs/docs/configuration/object_detectors.md
Clarity for the end user and correct uses of words
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Update docs/docs/frigate/installation.md
typo
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* update Installation.md to clarify Hailo-8L installation process.
* Update docs/docs/frigate/hardware.md
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Update hardware.md add Inference time.
* Oops no new line at the end of the file.
* Update docs/docs/frigate/hardware.md typo
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Update dockerfile to download the ssd_modilenet_v1 model instead of having it in the repo.
* Updated dockerfile so it dose not download the model file.
add function to download it at runtime.
update model path.
* fix formatting according to ruff and removed unnecessary functions.
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Add support for TensorRT v10 (multiple api calls have changed)
* Remove unnecessary size check in TensorRT v10 block
* Refactor to reduce code duplication
* Fix wrong function name in new _get_binding_dtype function and only return input check (not assertion) in new _binding_is_input function
* Add space around TRT_VERSION variable assignment (=) to respect linting
* More linting fix
* Update frigate/detectors/plugins/tensorrt.py
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* More linting
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* ROCm AMD/GPU based build and detector, WIP
* detectors/rocm: separate yolov8 postprocessing into own function; fix box scaling; use cv2.dnn.blobForImage for preprocessing; assert on required model parameters
* AMD/ROCm: add couple of more ultralytics models; comments
* docker/rocm: make imported model files readable by all
* docker/rocm: readme about running on AMD GPUs
* docker/rocm: updated README
* docker/rocm: updated README
* docker/rocm: updated README
* detectors/rocm: separated preprocessing functions into yolo_utils.py
* detector/plugins: added onnx cpu plugin
* docker/rocm: updated container with limite label sets
* example detectors view
* docker/rocm: updated README.md
* docker/rocm: update README.md
* docker/rocm: do not set HSA_OVERRIDE_GFX_VERSION at all for the general version as the empty value broke rocm
* detectors: simplified/optimized yolov8_postprocess
* detector/yolo_utils: indentation, remove unused variable
* detectors/rocm: default option to conserve cpu usage at the expense of latency
* detectors/yolo_utils: use nms to prefilter overlapping boxes if too many detected
* detectors/edgetpu_tfl: add support for yolov8
* util/download_models: script to download yolov8 model files
* docker/main: add download-models overlay into s6 startup
* detectors/rocm: assume models are in /config/model_cache/yolov8/
* docker/rocm: compile onnx files into mxr files at startup
* switch model download into bash script
* detectors/rocm: automatically override HSA_OVERRIDE_GFX_VERSION for couple of known chipsets
* docs: rocm detector first notes
* typos
* describe builds (harakas temporary)
* docker/rocm: also build a version for gfx1100
* docker/rocm: use cp instead of tar
* docker.rocm: remove README as it is now in detector config
* frigate/detectors: renamed yolov8_preprocess->preprocess, pass input tensor element type
* docker/main: use newer openvino (2023.3.0)
* detectors: implement class aggregation
* update yolov8 model
* add openvino/yolov8 support for label aggregation
* docker: remove pointless s6/timeout-up files
* Revert "detectors: implement class aggregation"
This reverts commit dcfe6bbf6f.
* detectors/openvino: remove class aggregation
* detectors: increase yolov8 postprocessing score trershold to 0.5
* docker/rocm: separate rocm distributed files into its own build stage
* Update object_detectors.md
* updated CODEOWNERS file for rocm
* updated build names for documentation
* Revert "docker/main: use newer openvino (2023.3.0)"
This reverts commit dee95de908.
* reverrted openvino detector
* reverted edgetpu detector
* scratched rocm docs from any mention of edgetpu or openvino
* Update docs/docs/configuration/object_detectors.md
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* renamed frigate.detectors.yolo_utils.py -> frigate.detectors.util.py
* clarified rocm example performance
* Improved wording and clarified text
* Mentioned rocm detector for AMD GPUs
* applied ruff formating
* applied ruff suggested fixes
* docker/rocm: fix missing argument resulting in larger docker image sizes
* docs/configuration/object_detectors: fix links to yolov8 release files
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* support for other yolov models and config checks
* apply code formatting
* Information about core mask and inference speed
* update rknn postprocess and remove params
* update model selection
* Apply suggestions from code review
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* support rknn on all socs
* apply changes from review and fix post process bug
* apply code formatting
* update tip in object_detectors docs
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* support for other yolov models and config checks
* apply code formatting
* Information about core mask and inference speed
* update rknn postprocess and remove params
* update model selection
* Apply suggestions from code review
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Update to latest tensorrt (8.6.1) release
* Build trt libyolo_layer.so in container
* Update tensorrt_models script to convert models from the frigate container
* Fix typo in model script
* Fix paths to yolo lib and models folder
* Add S6 scripts to test and convert specified TensortRT models at startup.
Rearrange tensorrt files into a docker support folder.
* Update TensorRT documentation to reflect the new model conversion process and minimum HW support.
* Fix model_cache path to live in config directory
* Move tensorrt s6 files to the correct directory
* Fix issues in model generation script
* Disable global timeout for s6 services
* Add version folder to tensorrt model_cache path
* Include TensorRT version 8.5.3
* Add numpy requirement prior to removal of np.bool
* This TRT version uses a mixture of cuda dependencies
* Redirect stdout from noisy model conversion
