0.17.0 Beta 1 #21274
Replies: 139 comments 530 replies
-
|
Has the debug view been removed? |
Beta Was this translation helpful? Give feedback.
-
|
Sick. The ideas and pace of development is amazing. Y'all rock. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
The docker images linked above cant be pulled because they are missing the -beta1- in the uri. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
Can license plate recognition be restricted by specifying certain zones? In some areas that are too far away, the license plates are unclear, making it meaningless to perform recognition. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
Birdseye stops working when Restream option is enabled (I can see birdseye in Frigate when restream=false). |
Beta Was this translation helpful? Give feedback.
-
|
I managed to make 0.17.0-beta work with intel arc b-series GPU using the same set of extra steps I described here #21257. The only difference is that now with 0.17 I can specify |
Beta Was this translation helpful? Give feedback.
-
|
Holy crap. So many new stuff that I have to postpone understanding it all until I can sit down to properly read and try one by one. Amazing major updates as usual. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
Wow, THANKS! There are a lot of great new things in v0.17 Bug report: I needed to provide the detection resolution and fps in the config file, otherwise the ffprobe command would hang and the frontend would wait forever for the backend to be ready. It may have something to do with my docker-compose using bridge network instead of host. Here is the fix: and here is what was hanging inside the container: and it did not help to try to get it to use TCP by adding a URL parameter in the camera's path in config. Here is the similar hanging process: a perhaps separate minor issue is that the logs print this line: This might be because my docker-compose does NOT use host networking as recommended by go2rtc for Homekit (see https://github.com/AlexxIT/go2rtc/blob/7e0c7a8173573d11c13f1ed90bb49c8702336d71/docker/README.md?plain=1#L16 ) . |
Beta Was this translation helpful? Give feedback.
-
|
Dann... what a great release Full of high quality features. Thx so much for Everything. BJ |
Beta Was this translation helpful? Give feedback.
-
|
First, I want to say awesome release and definitely unexpected this soon. I've immediately noticed a decrease in the number of stationary car objection detections (just a few now). I just made my first Object Classification model for known vehicles, but, after new clips are added to the queue, when attempting to start "Train Model" again, I get the following errors: I think the JWT error is unrelated, but I haven't encountered it before. I do notice the "Train Model" button is red, but I have 52 in the queue for retraining. I couldn't find any mention of a minimum number for retraining in the updated docs, however. |
Beta Was this translation helpful? Give feedback.
-
|
Got this error on first, and subsequent starts of this beta. Any ideas? |
Beta Was this translation helpful? Give feedback.
-
|
Apologies for this basic question but is this the correct image to use if I wish to use Coral TPU for object detection, and Nvidia GPU for hardware acceleration and enrichments? ghcr.io/blakeblackshear/frigate:0.17.0-beta1 What do I need to put in my docker compose file for my intent? |
Beta Was this translation helpful? Give feedback.
-
|
After a bit of tinkering, I got Ollama Cloud working without needing any local device to act as a shim. Before that, I was running # this won't work
genai:
provider: ollama
base_url: https://ollama.com
model: qwen3-vl:235b-instruct-cloud
api_key: '{FRIGATE_OLLAMA_CLOUD_API_KEY}'Thankfully though, Ollama Cloud offers an openai compatible endpoint at So, I set the env vars: OPENAI_BASE_URL=https://ollama.com/v1
FRIGATE_OLLAMA_CLOUD_API_KEY=mysupersecretrealkeyfromollamadotcomand used the following global configuration: genai:
provider: openai
model: qwen3-vl:235b-instruct
api_key: '{FRIGATE_OLLAMA_CLOUD_API_KEY}'and... success. I enabled review summaries on my outdoor cams and they are really accurate and really fast with this model/provider. Hope that this is helpful to some folks. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
The past few days my frigate has been crapping out and shutting down on me. I am running hcr.io/blakeblackshear/frigate:047ae19 because there were a few fixes you made that I wanted to take advantage of. It had been running fine for a while, but now it is crashing after 30 mins or so of running. Logs attached. |
Beta Was this translation helpful? Give feedback.
-
|
Some observations about using Core Ultra NPU for detection. For reference I'm using Yolov9s 320x320 with 7 camera streams. Frigate is installed in docker container on top of Debian Trixie.
Thanks and keep up the awesome work! |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
Not sure if anyone else is having similar issues. Going from latest stable to this beta caused the auth page to come up even with auth set to false in the config. Seems a bit more snappy for our 100+ setup but might be because its 1AM here... will report any other issues / notes if i find any. Thanks for all the work on this, you guys rock! |
Beta Was this translation helpful? Give feedback.
-
|
I have always wondered, would it make sense to add a link in Frigate that can be clicked to go directly to Frigate+ to verify images and etc?? |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
I'm loosing my mind.... I described my issue yesterday, and evry moment I'm awake I'm trying different ways to fix it. Can I get REAL HUMAN help? (AI sux and just wastes my time, both here and in docs) So I'm trying to add custom input_args for Reolink E1 Outdoor camera and hoping that will solve timestamp problem that causes ffmpeg to crash and playback not working properly. Problem is that I cannot find a way to provide those input_args without either container errors or figate UI errors (error in config). I tried, putting them in global, in camera, in stream, list, single line etc.... nothing works... Here is what I try to do (version with input_args per stream, full config and setup listed in linked thread): I would be really grateful for some real help here. |
Beta Was this translation helpful? Give feedback.
-
|
I got constant error and no detection with hikvision camera with latest build: |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
I think I've found out why my yard camera often loses continuous tracking of stationary objects. It's because my yard camera switches between infrared and color modes, and my cheap camera has significant overexposure when switching from color to infrared mode, with the screen brightness taking 2.5 seconds to stabilize. I've tried adjusting the lightning_threshold from 0.8 to 0.3, but none of these settings have effectively solved the problem. |
Beta Was this translation helpful? Give feedback.


















Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Beta docs: https://deploy-preview-19787--frigate-docs.netlify.app/
Images
Major Changes for 0.17.0
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:
frigate.dbfilegenaiconfig now only configures the provider. Other fields have moved underobjects -> genai. See the new GenAI documentation.record -> continuousandrecord -> motionare separate config fields. See the examples in the documentation.smallmodel, which performs well on both CPU and GPU. Thelargemodel is the same as 0.16's and is not as accurate as the upgradedsmallmodel in 0.17. Uselargeonly if you live in a region with multi-line plates and you are having issues detecting text on them with thesmallmodel.New Features
Frigate 0.17 introduces several major new features.
Classification Model Training
Frigate 0.17 supports classification models in two separate types: state classification and object classification. These models are trained locally on your machine using
ImageNetviaMobileNetV2.State Classification
State classification allows you to choose a certain region of camera(s) with multiple states, and train on images showing these states. For example, you could create a state classification model to determine if a gate is currently open or closed.
See the documentation.
Object Classification
Object classification allows you to choose an object type, like
dog, and classify specific dogs. For example, you can train the model to classify your dogFidoand add a sub label, while not labeling unknown dogs. Another example would be classifying if a person in a construction site is wearing a helmet or not.See the documentation.
Custom Viewer Roles
Frigate 0.17 now has the ability to create additional viewer user roles to limit access to specific cameras. Users with the
adminrole can create a uniquely named role from the UI (orauth --> rolesin the config) and assign at least one camera to it. Users assigned to the new role will have:viewerrole has access to (Live, Review/History, Explore, Exports), but only to the assigned camerasSee the documentation.
Review Item Summary with GenAI
Frigate 0.17 supports using GenAI to summarize review items. Unlike object descriptions which add a searchable description, review summaries have a structured output that instruct the AI provider to generate a title, description, and classify the activity as dangerous, suspicious, or normal.
This information is displayed in the UI automatically making it easier to see when activity requires further review and easier to understand what is happening during a particular video segment.
See the documentation.
Semantic Search Triggers
Triggers utilize Semantic Search to automate actions when a tracked object matches a specified image or description. Triggers can be configured so that Frigate executes a specific actions when a tracked object's image or description matches a predefined image or text, based on a similarity threshold. Triggers are managed per camera and can be configured via the Frigate UI in the Settings page under the Triggers tab.
See the documentation.
Object Detector Improvements
Frigate 0.17 brings performance increases for many detectors as well as support for new object detection hardware.
Nvidia GPU Performance
Support for Nvidia GPUs has been enhanced by implementing CUDA Graphs. CUDA Graphs work to reduce the involvement of the CPU for each inference, leading to faster inference times and lower CPU usage. CUDA graphs do have some limitations based on the complexity of the model, which means that YOLO-NAS, Semantic Search, and LPR models are not accelerated with CUDA Graphs. They will still continue to run on GPU as they did before.
Intel OpenVINO
Frigate 0.17 supports running models on Intel NPUs, for many models performance on NPU is similar to GPU but more efficient, leaving room to run more enrichment features on the GPU.
OpenVINO has also had many optimizations put in place to reduce memory and CPU utilization for object detection.
RKNN
Frigate 0.17 brings several improvements to RKNN platform including:
largemodel sizes.Apple Silicon
Frigate 0.17 supports running object detection on Apple Silicon NPU. This is provided through the Apple Silicon Detector which runs on the host and connects via IPC proxy to Frigate, providing fast and efficient inferences when run within the same Apple device.
See the documentation.
YOLOv9 on Google Coral
Frigate 0.17 supports running a quantized version of
YOLOv9on Coral devices, bringing improved accuracy over the defaultmobiledetmodel. Note that due to hardware limitations, only a subset of the objects on the standard COCO labelmap is included. YOLOv9 Frigate+ models are not supported on Coral at this time.See the documentation.
New Community Supported Detectors
Frigate 0.17 has community support for several new object detectors:
Frontend Improvements
In addition to supporting the new features, the frontend has many improvements.
Detail Stream
History view in 0.17 supports an additional view mode, Detail. This mode shows a card for each review item, and expanding a card reveals all tracked objects and their lifecycle events. Selecting any lifecycle event seeks the video to that exact timestamp. You can also overlay a tracked object's path on the video to help with debugging.
Redesigned Tracked Object Details pane
The Tracked Object Details pane in Explore has been redesigned to streamline the layout and consolidate related information. The Object Lifecycle tab is now the Tracking Details tab, which displays video overlays of the tracked object instead of static images, giving a clearer and more intuitive view of its activity.
Revamped Settings
Frigate 0.17 has a revamped Settings menu with a sidebar that categorizes the available options. This brings more scalability which will make it easier to support full UI configuration in a future version.
NOTE: The Debug view has been moved to the single camera Live view instead of Settings. Access the Debug view by enabling the switch under the Live view settings (cog icon) menu.
Add Camera Wizard
Frigate 0.17 supports adding camera via the UI without manually modifying your configuration file. When installing and starting Frigate for the first time, the main dashboard will include a button to start adding cameras via the Wizard.
Access the Wizard from the
Cameras --> Managementpage in Settings.Update Without Restarting
Frigate 0.17 supports saving many more features dynamically. Cameras, zones, and masks will not require a restart to take effect when saved through the UI. More will come in future versions.
Configuration Safe Mode
If an invalid configuration is detected, Frigate will enter safe mode and highlight the location of the issue. While in safe mode, the frontend is limited to the configuration editor, making it easy to correct the problem directly in the UI without needing an external file editor.
Other Notable Frontend Improvements
Other Backend Features and Improvements
Audio Transcription and Analysis
Frigate 0.17 supports fully local audio transcription using either
sherpa-onnxorfaster-whisper. The single camera Live view in the Frigate UI supports live transcription of audio for streams defined with the audio role, and anyspeechevents in Explore can be transcribed and/or translated through the Transcribe button in the Tracked Object Details pane.See the documentation.
Process and Efficiency Improvements
Frigate 0.17 uses the forkserver spawn method, this allows for better segmented memory control and better process management. Some processes are also started with lower priority, allowing the most important processes to have more CPU time when it is required.
Review Item Improvements
Review items have been refined to behave more intuitively:
Revamped stationary object tracking. Stationary object tracking has been enhanced to use new features to reduce incorrectly marking objects as active:
Smarter handling of loitering objects. Stationary behavior is now dynamic based on object type. Objects that are normally stationary for long periods (e.g., cars) will no longer keep a review item active indefinitely when stopped inside a loitering zone. Objects that are not expected to remain still (e.g., people) will continue the review item as long as they stay within the zone.
Severity-based review item cutoff. Review items now end when a higher-severity event (such as an
alertfor arriving home) finishes. Ongoing lower-severity motion (e.g., passing cars) will no longer keep the higher-severity review item alive. In these cases, thealertends and a newdetectionreview item begins immediately.Enrichment Improvements
-,, etc. to ensure that plates are more consistently recognized as the same plate. Documentationdeviceconfig option. This is useful in cases when multiple GPUs are available. DocumentationOther Improvements
networking -> ipv6 -> enabled. DocumentationThis discussion was created from the release 0.17.0 Beta 1.
Beta Was this translation helpful? Give feedback.
All reactions