* Adjust title prompt to have less rigidity
* Improve motion boxes handling for features that don't require motion
* Improve handling of classes starting with digits
* Improve vehicle nuance
* tweak lpr docs
* Improve grammar
* Don't allow # in face name
* add password requirements to new user dialog
* change password requirements
* Clenaup
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Fix jetson stats reading
* Return result
* Avoid unknown class for cover image
* fix double encoding of passwords in camera wizard
* formatting
* empty homekit config fixes
* add locks to jina v1 embeddings
protect tokenizer and feature extractor in jina_v1_embedding with per-instance thread lock to avoid the "Already borrowed" RuntimeError during concurrent tokenization
* Capitalize correctly
* replace deprecated google-generativeai with google-genai
update gemini genai provider with new calls from SDK
provider_options specifies any http options
suppress unneeded info logging
* fix attribute area on detail stream hover
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Use thread lock for JinaV2 call as it sets multiple internal fields while being called
* fix audio label translation in explore filter
* Show event in all cases, even without non-none match
* improve i18n key fallback when translation files aren't loaded
just display a valid time now instead of "invalid time"
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Add shortSummary field to review summary to be used for notifications
* pull in current config version into default config
* fix crash when dynamically adding cameras
depending on where we are in the update loop, camera configs might not be updated yet and we are receiving detections already
* add no tracked objects and icon to explore summary view
* reset add camera wizard when closing and saving
* don't flash no exports icon while loading
* Improve handling of homekit config
* Increase prompt tokens reservation
* Adjust
* Catch event not found object detection
* Use thread lock for JinaV2 in onnxruntime
* remove incorrect embeddings process from memray docs
* only show transcribe button if audio event has video
* apply aspect ratio and margin constraints to path overlay in detail stream on mobile
improves a specific case where the overlay was not aligned with 4:3 cameras on mobile phones
* show metadata title as tooltip on icon hover in detail stream
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* use fallback timeout for opening media source
covers the case where there is no active connection to the go2rtc stream and the camera takes a long time to start
* Add review thumbnail URL to integration docs
* fix weekday starting point on explore when set to monday in UI settings
* only show allowed cameras and groups in camera filter button
* Reset the wizard state after closing with model
* remove footnote about 0.17
* 0.17
* add triggers to note
* add slovak
* Ensure genai client exists
* Correctly catch JSONDecodeError
* clarify docs for none class
* version bump on updating page
* fix ExportRecordingsBody to allow optional name field
fixes https://github.com/blakeblackshear/frigate/discussions/21413 because of https://github.com/blakeblackshear/frigate-hass-integration/pull/1021
* Catch remote protocol error from ollama
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Send preferred language for report service
* make object lifecycle scrollable in tracking details
* fix info popovers in live camera drawer
* ensure metrics are initialized if genai is enabled
* docs
* ollama cloud model docs
* Ensure object descriptions get claened up
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Fix genai callbacks in MQTT
* Cleanup cursor pointer for classification cards
* Cleanup
* Handle unknown SOCs for RKNN converter by only using known SOCs
* don't allow "none" as a classification class name
* change internal port user to admin and default unspecified username to viewer
* keep 5000 as anonymous user
* suppress tensorflow logging during classification training
* Always apply base log level suppressions for noisy third-party libraries even if no specific logConfig is provided
* remove decorator and specifically suppress TFLite delegate creation messages
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Exclude D-FINE from using CUDA Graphs
* fix objects count in detail stream
* Add debugging for classification models
* validate idb stored stream name and reset if invalid
fixes https://github.com/blakeblackshear/frigate/discussions/21311
* ensure jina loading takes place in the main thread to prevent lazily importing tensorflow in another thread later
reverts atexit changes in https://github.com/blakeblackshear/frigate/pull/21301 and fixes https://github.com/blakeblackshear/frigate/discussions/21306
* revert old atexit change in bird too
* revert types
* ensure we bail in the live mode hook for empty camera groups
prevent infinite rendering on camera groups with no cameras
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Wait for config to load before evaluating route access
Fix race condition where custom role users are temporarily denied access after login while config is still loading. Defer route rendering in DefaultAppView until config is available so the complete role list is known before ProtectedRoute evaluates permissions
* Use batching for state classification generation
* Ignore incorrect scoring images if they make it through the deletion
* Delete unclassified images
* mitigate tensorflow atexit crash by pre-importing tflite/tensorflow on main thread
Pre-import Interpreter in embeddings maintainer and add defensive lazy imports in classification processors to avoid worker-thread tensorflow imports causing "can't register atexit after shutdown"
* don't require old password for users with admin role when changing passwords
* don't render actions menu if no options are available
* Remove hwaccel arg as it is not used for encoding
* change password button text
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
- don't look for event ids when trigger type is description
- don't try to delete thumbnail whe trigger type is description
- pass correct event ID into thumbnail deletion
* fix: Resolve deadlock and attribute error in embedding maintainer initialization
Updates the trigger embedding calculation to call embedding methods directly instead of using ZMQ. This prevents a deadlock during initialization where the ZMQ responder is not yet polling for requests.
Also updates sync_triggers to pass the camera name and trigger name to the calculation method, fixing an AttributeError where trigger.name was accessed on a TriggerConfig object.
* mocked repro
* Revert "mocked repro"
This reverts commit dea5b5d4db.
* fix formatting
* Update embeddings.py
new line
* update live view docs
* use swr as single source of truth for searchDetail
rather than maintaining a separate state, derive the selected item from swr cache. fixes websocket sync when regenerating descriptions or fetching transcriptions
* fix key warning in console
* don't try to fetch event from review item for audio events
* update audio transcription toast wording
* Add a community supported badge to specific detectors in the info summaries to better separate
* Make object classification publish to tracked object update and add examples for state classification
* Add item to advanced docs about tensorflow limiting
* Don't show submission for in progress objects
* fix for ios not reporting video dimensions on initial metadata load
in testing, polling with requestAnimationFrame finds the dimensions within 2 frames
* Catch jetson nvidia device tree
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Don't warn when event ids have expired for trigger sync
* Import faster_whisper conditinally to avoid illegal instruction
* Catch OpenVINO runtime error
* fix race condition in detail stream context
navigating between tracked objects in Explore would sometimes prevent the object track from appearing
* Handle case where classification images are deleted
* Adjust default rounded corners on larger screens
* Improve flow handling for classification state
* Remove images when wizard is cancelled
* Improve deletion handling for classes
* Set constraints on review buffers
* Update to support correct data format
* Set minimum duration for recording based review items
* Use friendly name in review genai prompt
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* remove frigate+ icon from explore grid footer
* add margin
* pointer cursor on event menu items in detail stream
* don't show submit to plus for non-objects and if plus is disabled
* tweak spacing in annotation settings popover
* Fix deletion of classification images and library
* Ensure after creating a class that things are correct
* Fix dialog getting stuck
* Only show the genai summary popup on mobile when timeline is open
* fix audio transcription embedding
* spacing
* hide x icon on restart sheet to prevent closure issues
* prevent x overflow in detail stream on mobile safari
* ensure name is valid for search effect trigger
* add trigger to detail actions menu
* move find similar to actions menu
* Use a column layout for MobilePageContent in PlatformAwareSheet
This is so the header is outside the scrolling area and the content can grow/scroll independently. This now matches the way it's done in classification
* Skip azure execution provider
* add optional ref to always scroll to top
the more filters in explore was not scrolled to the top on open due to the use of framer motion
* fix title classes on desktop
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Correctly remove classification model from config
* Undo
* fix
* Use existing config update API and dynamically remove models that were running
* Set update message for face
* Implement extraction of images for classification state models
* Add object classification dataset preparation
* Add first step wizard
* Update i18n
* Add state classification image selection step
* Improve box handling
* Add object selector
* Improve object cropping implementation
* Fix state classification selection
* Finalize training and image selection step
* Cleanup
* Design optimizations
* Cleanup mobile styling
* Update no models screen
* Cleanups and fixes
* Fix bugs
* Improve model training and creation process
* Cleanup
* Dynamically add metrics for new model
* Add loading when hitting continue
* Improve image selection mechanism
* Remove unused translation keys
* Adjust wording
* Add retry button for image generation
* Make no models view more specific
* Adjust plus icon
* Adjust form label
* Start with correct type selected
* Cleanup sizing and more font colors
* Small tweaks
* Add tips and more info
* Cleanup dialog sizing
* Add cursor rule for frontend
* Cleanup
* remove underline
* Lazy loading
* camera level config
* set up model runner on thread start to avoid unpickling error
* ensure feature is enabled globally
* suppress info logs from faster_whisper
* fix incorrect event_type for api and audio timeline entries
* docs
* fix
* clean up
* refactor get_video_properties and use json output from ffprobe
* add zmq topic
* publish valid segment data in recording maintainer
* check for valid video data
- restart separate record ffmpeg process if no video data has been received in 120s
- refactor datetime import
* listen to correct topic in embeddings maintainer
* refactor to move get_latest_segment_datetime logic to recordings maintainer
* debug logging
* cleanup
* continue to use paddleocr v3 text detection model for large
v5 was not finding text on multi-line plates at all in testing
* implement clustering of plate variants per event
should reduce OCR inconsistencies and improve plate recognition stability by using string similarity to cluster similar variants (10 per event id) and choosing the highest confidence representative as the final plate
* pass camera
* prune number of variants based on detect fps
* implement replacement rules for cleaning up and normalizing plates
* docs
* docs
* Cleanup onnx detector
* Fix
* Fix classification cropping
* Deprioritize openvino
* Send model type
* Use model type to decide if model can use full optimization
* Clenanup
* Cleanup
* Use re-usable inference request to reduce CPU usage
* Share tensor
* Don't count performance
* Create openvino runner class
* Break apart onnx runner
* Add specific note about inability to use CUDA graphs for some models
* Adjust rknn to use RKNNRunner
* Use optimized runner
* Add support for non-complex models for CudaExecutionProvider
* Use core mask for rknn
* Correctly handle cuda input
* Cleanup
* Sort imports
* Generate review item summaries with requests
* Adjust logic to only send important items
* Don't mention ladder
* Adjust prompt to be more specific
* Add more relaxed nature for normal activity
* Cleanup summary
* Update ollama client
* Add more directions to analyze the frames in order
* Remove environment from prompt
* Include extra level for normal activity
* Add dynamic toggling
* Update docs
* Add different threshold for genai
* Adjust webUI for object and review description feature
* Adjust config
* Send on startup
* Cleanup config setting
* Set config
* Fix config name
* semantic trigger test
* database and model
* config
* embeddings maintainer and trigger post-processor
* api to create, edit, delete triggers
* frontend and i18n keys
* use thumbnail and description for trigger types
* image picker tweaks
* initial sync
* thumbnail file management
* clean up logs and use saved thumbnail on frontend
* publish mqtt messages
* webpush changes to enable trigger notifications
* add enabled switch
* add triggers from explore
* renaming and deletion fixes
* fix typing
* UI updates and add last triggering event time and link
* log exception instead of return in endpoint
* highlight entry in UI when triggered
* save and delete thumbnails directly
* remove alert action for now and add descriptions
* tweaks
* clean up
* fix types
* docs
* docs tweaks
* docs
* reuse enum
* Ignore numpy get limits warning
* Add function wrapper to redirect stdout and stderr to logpipe
* Save stderr too
* Add more to catch
* run logpipe
* Use other logging redirect class
* Use other logging redirect class
* add decorator for redirecting c/c++ level output to logger
* fix typing
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Move log level initialization to log
* Use logger config
* Formatting
* Fix config order
* Set process names
---------
Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
* Set runtime
* Use count correctly
* Don't assume camera sizes
* Use separate zmq proxy for object detection
* Correct order
* Use forkserver
* Only store PID instead of entire process reference
* Cleanup
* Catch correct errors
* Fix typing
* Remove before_run from process util
The before_run never actually ran because:
You're right to suspect an issue with before_run not being called and a potential deadlock. The way you've implemented the run_wrapper using __getattribute__ for the run method of BaseProcess is a common pitfall in Python's multiprocessing, especially when combined with how multiprocessing.Process works internally.
Here's a breakdown of why before_run isn't being called and why you might be experiencing a deadlock:
The Problem: __getattribute__ and Process Serialization
When you create a multiprocessing.Process object and call start(), the multiprocessing module needs to serialize the process object (or at least enough of it to re-create the process in the new interpreter). It then pickles this serialized object and sends it to the newly spawned process.
The issue with your __getattribute__ implementation for run is that:
run is retrieved during serialization: When multiprocessing tries to pickle your Process object to send to the new process, it will likely access the run attribute. This triggers your __getattribute__ wrapper, which then tries to bind run_wrapper to self.
run_wrapper is bound to the parent process's self: The run_wrapper closure, when created in the parent process, captures the self (the Process instance) from the parent's memory space.
Deserialization creates a new object: In the child process, a new Process object is created by deserializing the pickled data. However, the run_wrapper method that was pickled still holds a reference to the self from the parent process. This is a subtle but critical distinction.
The child's run is not your wrapped run: When the child process starts, it internally calls its own run method. Because of the serialization and deserialization process, the run method that's ultimately executed in the child process is the original multiprocessing.Process.run or the Process.run if you had directly overridden it. Your __getattribute__ magic, which wraps run, isn't correctly applied to the Process object within the child's context.
* Cleanup
* Logging bugfix (#18465)
* use mp Manager to handle logging queues
A Python bug (https://github.com/python/cpython/issues/91555) was preventing logs from the embeddings maintainer process from printing. The bug is fixed in Python 3.14, but a viable workaround is to use the multiprocessing Manager, which better manages mp queues and causes the logging to work correctly.
* consolidate
* fix typing
* Fix typing
* Use global log queue
* Move to using process for logging
* Convert camera tracking to process
* Add more processes
* Finalize process
* Cleanup
* Cleanup typing
* Formatting
* Remove daemon
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Add base class for global config updates
* Add or remove camera states
* Move camera process management to separate thread
* Move camera management fully to separate class
* Cleanup
* Stop camera processes when stop command is sent
* Start processes dynamically when needed
* Adjust
* Leave extra room in tracked object queue for two cameras
* Dynamically set extra config pieces
* Add some TODOs
* Fix type check
* Simplify config updates
* Improve typing
* Correctly handle indexed entries
* Cleanup
* Create out SHM
* Use ZMQ for signaling object detectoin is completed
* Get camera correctly created
* Cleanup for updating the cameras config
* Cleanup
* Don't enable audio if no cameras have audio transcription
* Use exact string so similar camera names don't interfere
* Add ability to update config via json body to config/set endpoint
Additionally, update the config in a single rather than multiple calls for each updated key
* fix autotracking calibration to support new config updater function
---------
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
* Combine base and arm trt detectors
* Remove unused deps for amd64 build
* Add missing packages and cleanup ldconfig
* Expand packages for tensorflow model training
* Cleanup
* Refactor training to not reserve memory
