frigate

blakeblackshear/frigate

Fork 0

mirror of https://github.com/blakeblackshear/frigate.git synced 2025-12-10 00:07:21 -06:00

RSS Feed

v0.16.0-beta1 5c3ac75c31
0.16.0 Beta 1 Pre-Release

giteasync released this 2025-05-02 18:35:55 -05:00 | 912 commits to dev since this release
Beta Documentation: https://deploy-preview-16390--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.16.0-beta1
- ghcr.io/blakeblackshear/frigate:0.16.0-beta1-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.16.0-beta1-tensorrt
- ghcr.io/blakeblackshear/frigate:0.16.0-beta1-rk
- ghcr.io/blakeblackshear/frigate:0.16.0-beta1-rocm
- ghcr.io/blakeblackshear/frigate:0.16.0-beta1-tensorrt-jp6
Major Changes for 0.16.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- The go2rtc audio handling has been updated to accept any audio codec instead of only AAC. This makes it easier to get audio from cameras that use PCMA/U audio. However, if the recording ffmpeg preset preset-record-generic-audio-copy is currently used it likely will need to be changed to preset-record-generic-audio-aac to continue to support audio in recordings.
```
ffmpeg:
  ...
  output_args: 
    record: preset-record-generic-audio-aac
```
- Object detection is now disabled by default. A config migrator will update your config globally with enabled: true for detect:. If you use Frigate with a read-only config, you may need to edit your own config to enable object detection manually.
```
detect:
  enabled: true
```
- Frigate will no longer fall back to look for a ffmpeg binary in PATH. If you are extending the Frigate image or somehow injecting a custom ffmpeg binary in a place like /usr/local/bin, please read the custom ffmpeg build guide.
- Home Assistant Add-on users will need to be aware of several important breaking changes. See the Important Notes for Home Assistant Add-on Users section below.
- The base image for Frigate has been updated to Debian Bookworm. The Jetpack 4 (jp4) and Jetpack 5 (jp5) images have been removed due to not being compatible with the new base image. A new Jetson Jetpack 6 (jp6) build has been contributed by a community member.
- The camera group icon pack has been updated. Some of your camera group icons may need to be re-selected.
- The Hailo driver and firmware has been updated to 1.20.1. The standard Docker image now provides Hailo support. If you are using Home Assistant Operating System, version 15.0 is required. Other users will need to update the Hailo driver and firmware on their system using the user installation script.
- The ROCm migraphx detector has been removed: Instead of separately supporting ROCm via MigraphX and via ONNX, the ROCm (rocm) detector has been removed, and the onnx detector should be used instead. This change should only require changing the type: rocm to type: onnx in detectors
- An additional parameter has been added to movement_weights for autotracking users. A config migrator will add the new value so that Frigate starts, but if this fails or you are using relative zooming with autotracking, you should remove movement_weights from your config and recalibrate.
Important Notes for Home Assistant Add-on Users

For Home Assistant add-on users only

The Frigate config directory for add-on users was changed from the Home Assistant config directory to the add-on config directory. With this change, the Frigate config file and database are now part of the add-on backup taken by Home Assistant, no longer needing to backup them manually. Note that only backups after 0.16 will benefit of this change. If you took a backup of Frigate 0.15 when updating to 0.16, the Frigate config file and database will not be part of it. In that case, you should still backup them manually before updating to Frigate 0.16.

Automatic migration

Upon the first Frigate 0.16 initialization, all Frigate-related files will be moved from the Home Assistant config directory to the Frigate add-on config directory. This will mean these files will no longer be accessible through your Home Assistant /config directory. They will now be found in the /addon_configs directory, which can also be accessed through the Terminal or VS Code add-ons.

In the new directory, the Frigate config file will be named config.yml rather than frigate.yml. This aligns with people running Frigate through other means. If you want to move back to Frigate 0.15 and did not backup the config file, you can copy the config.yml from the /addons_config back to /config/frigate.yml before restoring the add-on. Consider copying back other files as well, like custom model, custom ffmpeg, and custom go2rtc. Note that the database from 0.16 is not compatible with Frigate 0.15 anyway and thus should not be copied back. To restore the database, you must restore it from a manual backup.

Moving the config directory between add-on variants

The /addon_configs directory contains the config directories of all add-ons. You can move files from one addon config directory to another, like from Frigate Beta to the stable one, or vice-versa. Make sure you do that before uninstalling the add-on, unless you do not select the Also permanently delete this addon's data when uninstalling it.

Breaking change

If your Frigate config file refers to any arbitrary files in the Home Assistant config dir, like echo:/config/ scripts, their references must be manually updated to from /config/ to /homeassistant/.

New Features

Frigate 0.16 introduces several major new features.

Face Recognition

Frigate utilizes face detection and recognition to apply sub-labels to known faces. Recognized faces can be included in built-in notifications and integrated into third-party notifications.

Frigate+ is not required to use Face Recognition. However, using a Frigate+ model (or a custom model that detects face natively) enhances efficiency by eliminating the need for separate face detection per person.

The accuracy of face recognition heavily depends on the quality of the images used for training. It is highly recommended to follow the training guide to achieve the best results.

Refer to the Face Recognition documentation for more.

License Plate Recognition (LPR)

Frigate detects and recognizes license plates, saving recognized plates to tracked car objects. Known license plates can also be assigned custom labels (e.g., AB12345 --> Bob's Car).

Frigate+ is not required for License Plate Recognition. However, using a Frigate+ model (or a custom model that detects license_plate natively) improves efficiency by eliminating the need for a separate detection model.

For additional features such as regex-based matching, refer to the License Plate Recognition documentation.

Viewer Role

Frigate 0.16 introduces a Viewer role that restricts access to system features, the configuration editor, and the Frigate HTTP API. Viewers have permissions to use the Live view, Review, and Explore.

Additionally, each user can mark review items as reviewed independently so that one user's action will not hide the review items from others.

The Users tab in Settings can be used to create users and assign roles, and these roles are enforced when accessing Frigate through the authenticated port. Documentation

More fine-grained permissions (like denying access to specific cameras, for example) will come in a future version.

Proxies can also now map user roles. See the Proxy configuration documentation.

Improved Support For Object Detection Hardware and Models

Hailo8

The Hailo8 detector has been refactored by the Hailo team to greatly improve object detection performance and to add support for more model types. Documentation

ONNX & OpenVINO

Support has been added for a variety of new models for ONNX and OpenVINO detectors
- Frigate now supports state-of-the-art D-FINE and RF-DETR models via the ONNX and OpenVINO detectors. Documentation
- Add YOLOv3, YOLOv4, and YOLOv9 model support. Documentation
- Add YOLOx model support. Documentation
RockChip (RKNN)

RockChip has had the following improvements:
- GPU and NPU stats are now supported in the UI (this requires mapping /sys as read-only, see the docs for more information)
- RKNN Toolkit has been updated to 2.3.2
- There is now built in support for converting custom ONNX models to RKNN format
- Support has been added to the RKNN detector:
  - Built in support has been added for YOLOv9 models Documentation
  - Built in support has been added for YOLOx models Documentation
Camera Improvements

Dynamically Enable and Disable Cameras

Frigate now offers the ability to enable / disable cameras dynamically, including buttons in the UI, MQTT, and using the camera.turn_on / camera.turn_off services in the Home Assistant Integration. Disabling a camera stops all of Frigate's decoding and processing for that camera. See the documentation.

Live Stream Selection

Frigate now allows configuring multiple streams per camera, so that any number of streams for a single camera can be created and selected in the UI. See the Live view documentation.

Camera groups now include per-camera settings to further customize the live streaming behavior of that camera in that camera group.

Other noteworthy live streaming improvements:
- Create on demand recordings from the single camera Live view in the UI
- Audio can be enabled on Live view dashboards through a right-click context menu
- Streaming statistics make it easy to view live stream mode and performance
Other UI Changes

There are many other notable improvements to the Frigate UI:
- The review timeline has been rewritten to be more performant and support zooming using pinch-to-zoom on mobile and Ctrl + scroll wheel on desktop.
- Plot object paths in the Object Lifecycle pane.
- Add ability to create object masks from bounding boxes in the Object Lifecycle pane by right clicking.
- Add edge/point snapping to the Mask/Zone editor.
- Add the earliest recording date from the database to the Storage Metrics page.
- Add an underline for each day that recordings are available in the History calendar pane.
- Add a scroll bar to Logs pane and stream logs live as they are recorded.
- Add a Frigate+ pane to Settings to show model information and allow selection of a new model from the UI.
- Add the ability to draw a rectangle on the debug view to obtain an area (in pixels and percentage) and size ratio.
- Add the ability to edit sub labels directly in the Tracked Object Details pane.
- Ensure the mute/unmute state is persisted for the HLS player.
- Add camera selection to History view.
i18n Support

Frigate now supports internationalization and localization, making it possible to change the language of the UI. The language is auto-selected based on your browser locale and can also be changed via the Languages menu in the UI.

Some languages are not fully translated. Translation contributions are welcomed and can be made using Weblate.

Backend Features and Performance Improvements

New Base Image
- The base image for Frigate has been updated to Debian 12 ("Bookworm") and Python 3.11, bringing many backend performance improvements. WARNING: The popular tteck Proxmox LXC script won't automatically support Frigate 0.16. Changes will need to be made to the script. Proxmox remains an officially unsupported installation method.
Zones and Object Area
- Add the ability to estimate the speed of objects passing through zones and set a speed threshold to trigger zones. Documentation
- Adds the ability to specify min_area and max_area as a decimal between 0.000001 and .99 to represent a percentage of the frame. Numbers above 1 will still represent areas in pixels. For reference, 0.000001 represents ~1 pixel at 1280x720.
- The object area decimal value is now displayed wherever area pixels are displayed in the UI.
Semantic Search
- Semantic Search is now optional and no longer required to be enabled to use Generative AI.
- Jina V2 can now be used for Semantic Search, providing multi-lingual support. Documentation
- Add the ability to trigger the reindexing of tracked object embeddings directly from the UI.
Bird Classification
- Add the ability to classify detected birds and add the name to the tracked object's sub label. Documentation
ONVIF and Autotracking
- Implement ONVIF reconnect if a camera goes offline.
- Improve responsiveness of zooming when using relative zooming with autotracking.
- Refined object tracking parameters and use re-identification when autotracking the person object.
Other notable changes
- Export filenames now include the start and end date/time.
- Add title as mp4 metadata to exports.
- Add ability to specify cooldown time and suspend native notifications per camera. Documentation
- Add an API endpoint, /recordings/summary, to return true/false for each day that recordings are available.
- Implement de-duplication of log entries to prevent log flooding from the same message.
- Add support for SR-IOV GPU stats.
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.1 6cb5cfb0c9
0.15.1 Release Stable

giteasync released this 2025-04-11 17:23:13 -05:00 | 1395 commits to dev since this release
This is a maintenance release for Frigate 0.15 that includes two bugfixes.

What's Changed
- Fix crash in get_current_frame() (https://github.com/blakeblackshear/frigate/pull/16594)
- Fix trt model prepare script (https://github.com/blakeblackshear/frigate/pull/17661)
Images
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-rc2 93d39370b6
0.15.0 Release Candidate 2 Pre-Release

giteasync released this 2025-01-30 12:23:38 -06:00 | 1435 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-rc2-h8l
Changes since RC1
- Don't show sub labels in object filter list
- Fix autotracking interpolation when using absolute zoom
- Fix some h265 encoding presets
- Fix selection of tracked objects in Explore on desktop Safari
- Fix CSRF check not cancelling out the request
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- The nested model config under a detector has been simplified to just model_path as a string value. This change will be handled automatically through config migration.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0 cea210d800
0.15.0 Release Stable

giteasync released this 2025-01-30 11:27:38 -06:00 | 1436 commits to dev since this release
Images
Changes since RC2
- None
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- The nested model config under a detector has been simplified to just model_path as a string value. This change will be handled automatically through config migration.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Full Changelog: https://github.com/blakeblackshear/frigate/compare/v0.14.1...v0.15.0
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-rc1 6d8234fa27
0.15.0 Release Candidate 1 Pre-Release

giteasync released this 2025-01-24 09:45:46 -06:00 | 1443 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-rc1-h8l
Changes since Beta 7
- Fix bug that prevented typing certain characters in Tracked Object Details pane
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- The nested model config under a detector has been simplified to just model_path as a string value. This change will be handled automatically through config migration.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-beta7 83ac42cbdc
0.15.0 Beta 7 Pre-Release

giteasync released this 2025-01-18 22:33:13 -06:00 | 1448 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-beta7-h8l
Changes since Beta 6
- Fix for ffmpeg qsv args
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- The nested model config under a detector has been simplified to just model_path as a string value. This change will be handled automatically through config migration.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-beta6 3947e79086
0.15.0 Beta 6 Pre-Release

giteasync released this 2025-01-18 06:48:28 -06:00 | 1451 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-beta6-h8l
Changes since Beta 5
- Improvements to latest image API
- ffmpeg fixes for rockchip
- UI fixes
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- The nested model config under a detector has been simplified to just model_path as a string value. This change will be handled automatically through config migration.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-beta5 173b7aa308
0.15.0 Beta 5 Pre-Release

giteasync released this 2025-01-11 08:47:45 -06:00 | 1457 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-beta5-h8l
Changes since Beta 4
- Ability to save debug images for GenAI
- QSV ffmpeg changes for reolink compatibility
- Nested model config simplifications
- Fix for GPU stats when user has multiple Nvidia GPUs of same model
- Fix event cleanup error
- UI fixes and wording updates to simplify UI
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- The nested model config under a detector has been simplified to just model_path as a string value. This change will be handled automatically through config migration.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-beta4 87e7b62c85
0.15.0 Beta 4 Pre-Release

giteasync released this 2024-12-22 13:31:14 -06:00 | 1474 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-beta4-h8l
Changes since Beta 3
- Fix a bug with SHM frame names that prevented cameras from starting in some cases
- Ensure pre_capture and post_capture work correctly with refactored alerts/detections record config
- Fix a UI bug that caused an infinite loop when navigating to History from Explore
- Add the ability to specify tls_insecure for onvif cameras
- Catch onvif error when running an operation the camera doesn't support
- Catch OS error when checking storage utilization
- Fix a bug that caused identical thumbnails to be sent to a GenAI provider under certain circumstances
- Improve handling of error conditions with Ollama and snapshot regeneration
- Don't crop by region for GenAI snapshot for manual events
- Ensure go2rtc credentials are cleaned before returning the config
- Optimize HTTP requests with connection pooling for DeepStack detector
- Cap storage bandwidth at a logical maximum for storage cleanup
- Standardize handling of config files
- Return 401 for login failures
- Other minor UI fixes and tweaks
- Documentation updates
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)
v0.15.0-beta3 6b12a45a95
0.15.0 Beta 3 Pre-Release

giteasync released this 2024-12-10 07:42:55 -06:00 | 1502 commits to dev since this release
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/

Images
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-standard-arm64
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-tensorrt
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-tensorrt-jp4
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-tensorrt-jp5
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-rk
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-rocm
- ghcr.io/blakeblackshear/frigate:0.15.0-beta3-h8l
Changes since Beta 2
- SHM refactor and bugfixes
- Add ability to bulk delete tracked objects in Explore
- Add sorting to Explore
- Fix bug where audio events would not show in Explore
- Fix bug that caused a crash when creating external events
- Refactor cleanup to consider review severity
- Other minor UI fixes and tweaks
Major Changes for 0.15.0

Breaking Changes

There are several breaking changes in this release, Frigate will attempt to update the configuration automatically. In some cases manual changes may be required. It is always recommended to back up your current config and database before upgrading:
1. Simply copy your current config file to a new location
2. Stop Frigate and make a copy of the frigate.db file
- Rewritten SHM system
  - The SHM system has been rewritten to be more stable. This means that a large % of shared memory (SHM) will be used by default but the total usage will not fluctuate, and Frigate will not fail from SHM overflowing. However, this also means that having the correct SHM size for your cameras, detector, and hardware is more important to having a smooth experience with Frigate. A new calculation is done on startup, so if your shm_size is too low then a warning will be printed in the log stating that it needs to be increased.
- Recording configuration changed
  - The record config has been refactored to allow for direct control of how long alerts and detections are retained. These values will be automatically populated from your current config, but you may want to adjust the values that are set after updating. See the updated docs here and ensure your updated config retains the footage you want it to.
- ffmpeg updates
  - ffmpeg has been updated to version 7. Some Intel users may need to change what hwaccel preset they are using (preset-vaapi may need to now be preset-intel-qsv-h264 or preset-intel-qsv-h265) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If a qsv preset is not working properly, you may still need to use a preset-vaapi or revert to the previous ffmpeg version as described below.
  - The new version provides many improvements, but the old version can still be run if needed by specifying path: "5.0" in your ffmpeg: config entry. For example:
    ffmpeg: path: "5.0"
  - ffmpeg presets have been updated. It is always recommended to use ffmpeg presets rather than manual arguments.
  - ffmpeg is no longer part of $PATH. In most cases this is handled automatically.
    
    go2rtc exec streams will need to add the full path for ffmpeg which in most cases will be /usr/lib/ffmpeg/7.0/bin/ffmpeg.
    
    If the go2rtc config has bin: ffmpeg defined, it needs to be removed.
- Submitting to Frigate+
  - The Frigate+ view in the UI has been replaced by the new Explore view. See the notes below.
Explore

The new Explore pane in Frigate 0.15 makes it easy to explore every object tracked by Frigate. It offers a variety of filters and supports keyword and phrase-based text search, searching for similar images, and searching through descriptive text generated by AI models.

The default Explore pane shows a summary of your most recent tracked objects organized by label. Clicking the small arrow icon at the end of the list will bring you to an infinitely scrolling grid view. The grid view can also be set as the default by changing the view type from the Settings button in the top right corner of the pane.

The Explore pane also serves as the new way to submit images to Frigate+. Filters can be applied to only display tracked objects with snapshots that have not been submitted to Frigate+. The left/right arrow keys on the keyboard allow quick navigation between tracked object snapshots when looking at the Tracked Object Details pane from the grid view.

AI/ML Search

Frigate 0.15 introduces two powerful search features: Semantic Search and GenAI Search. Semantic Search can be enabled on its own, while GenAI Search works in addition to Semantic Search.

Semantic Search

Semantic Search uses a CLIP model to generate embeddings (numerical representations of images) for the thumbnails of your tracked objects, enabling searches based on text descriptions or visual similarity. This is all done locally.

For instance, if Frigate detects and tracks a car, you can use similarity search to see other instances where Frigate detected and tracked that same car. You can also quickly search your tracked objects using an "image caption" approach. Searching for "red car driving on a residential street" or "person in a blue shirt walking on the sidewalk at dawn" or even "a person wearing a black t-shirt with the word 'SPORT' on it" will produce some stunning results.

Semantic Search works by running an AI model locally on your system. Small or underpowered systems like a Raspberry Pi will not run Semantic Search reliably or at all. A dedicated GPU and 16GB of RAM is recommended for best performance.

See the Semantic Search docs for system requirements, setup instructions, and usage tips.

Generative AI

GenAI Search employs generative AI models to create descriptive text for the thumbnails of your tracked objects, which are stored in the Frigate database to enhance future searches. Supported providers include Google Gemini, Ollama, and OpenAI, so you can choose whether you want to send data to the cloud or use a locally hosted provider.

See the GenAI docs for setup instructions and use case suggestions.

Improved Tools for Debugging

Review Item Details Pane

A new Review Item Details pane can be viewed by clicking / tapping on the gray chip on a review item in the Review pane. This shows more information about the review item as well as thumbnails or snapshots for individual objects (if enabled). The pane also provides links to share the review item, download it, submit images to Frigate+, view object lifecycles, and more.

Object Lifecycle Pane

The Recordings Timeline from Frigate 0.13 has been improved upon and returns to 0.15 as the Object Lifecycle, viewable in the Review Details pane as well as the new Explore page. The new pane shows the significant moments during the object's lifecycle: when it was first seen, when it entered a zone, became stationary, etc. It also provides information about the object's area and size ratio to assist in configuring Frigate to tune out false positives.

Native Notifications

Frigate now supports notifications using the WebPush protocol. This allows Frigate to deliver notifications to devices that have registered to receive notifications in the Frigate settings, delivering them in a timely and secure manner. Currently, notifications will be delivered for all review items marked as alerts. More options for native notifications will be supported in the future.

See the notifications docs.

New Object Detectors

ONNX

ONNX is an open model standard which allows for a single model format that can run on different types of GPUs. The default, tensorrt, and rocm Frigate build variants include GPU support for efficient object detection via ONNX models, simplifying configuration and support more models. There are no default included ONNX models for object detection.

AMD MiGraphX

Support has been added for AMD GPUs via ROCm and MiGraphX. Currently there is no default included model for this detector.

Hailo-8

Support has been added for the Hailo8 and Hailo-8L hardware for object detection on both arm64 and amd64 platforms.

Other UI Changes
- Rework the Storage metrics pane to be more clear how much storage each camera is using
- Camera stream info button has been added to the camera metrics page allowing easy access to see camera codec information
- Add button for downloading the full set of logs
- The timeline handlebar will now automatically scroll while viewing recordings
- Review items and exports can now be shared via your browser's sharing pane or via direct link url. A secure context is required for the browser/OS sharing pane to function
- Add the ability to rename camera groups
- Add middle mouse button support in the Review pane to open full recordings view in a new tab
- Add Nvidia GPU encode and decode stats to system metrics
- New desktop keyboard shortcuts. In addition to the numerous keyboard shortcuts available with 0.14, 0.15 adds several more. In Live view, the numeric keys (1-9) will move PTZ cameras to presets. In Review, Page Up and Page Down will scroll through review items
- Accessibility updates for users with screen readers
Other Backend Changes
- FFMPEG updated to 7.0
- OpenVINO updated to 2024.3
- Use FastAPI instead of Flask for the Frigate API
- Add service manager infrastructure
- Install onevpl tools and update drivers for Intel
- If record is disabled for a camera then that camera will not save frames to the preview during that time
- Fix stalled connections to certain onvif cameras
- Fix autotracking absolute zoom interpolation logic
- TensorRT models are no longer generated by default, the ENV var must be set
Downloads
- Source Code (ZIP)
- Source Code (TAR.GZ)

1 2 3 4 5 ...

145 Releases 148 Tags

0.16.0 Beta 1 Pre-Release

Images

Major Changes for 0.16.0

Breaking Changes

Important Notes for Home Assistant Add-on Users

New Features

Face Recognition

License Plate Recognition (LPR)

Viewer Role

Improved Support For Object Detection Hardware and Models

Hailo8

ONNX & OpenVINO

RockChip (RKNN)

Camera Improvements

Dynamically Enable and Disable Cameras

Live Stream Selection

Other UI Changes

i18n Support

Backend Features and Performance Improvements

New Base Image

Zones and Object Area

Semantic Search

Bird Classification

ONVIF and Autotracking

Other notable changes

0.15.1 Release Stable

What's Changed

Images

0.15.0 Release Candidate 2 Pre-Release

Images

Changes since RC1

Major Changes for 0.15.0

Breaking Changes

Explore

AI/ML Search

Semantic Search

Generative AI

Improved Tools for Debugging

Review Item Details Pane

Object Lifecycle Pane

Native Notifications

New Object Detectors

ONNX

AMD MiGraphX

Hailo-8

Other UI Changes

Other Backend Changes

0.15.0 Release Stable

Images

Changes since RC2

Major Changes for 0.15.0

Breaking Changes

Explore

AI/ML Search

Semantic Search

Generative AI

Improved Tools for Debugging

Review Item Details Pane

Object Lifecycle Pane

Native Notifications

New Object Detectors

ONNX

AMD MiGraphX

Hailo-8

Other UI Changes

Other Backend Changes

0.15.0 Release Candidate 1 Pre-Release

Images

Changes since Beta 7

Major Changes for 0.15.0

Breaking Changes

Explore

AI/ML Search

Semantic Search

Generative AI

Improved Tools for Debugging

Review Item Details Pane

Object Lifecycle Pane

Native Notifications