0.15.0 Beta 2 #15097
Replies: 16 comments 92 replies
-
I have an issue with Beta2 not starting. UI partially loads but no cameras and all menu items give the spinny wheel
Reverting to beta1 and it starts ok
|
Beta Was this translation helpful? Give feedback.
-
I have a script that catches events via API, in this new beta 2 version it is giving the message: {"success":false,"message":"Event not found"} I'm using the API to get manual events |
Beta Was this translation helpful? Give feedback.
-
2GB. Beta 1 only uses around 22MB
…On Wed, 20 Nov 2024 at 14:52, Nicolas Mowen ***@***.***> wrote:
What is your SHM size
—
Reply to this email directly, view it on GitHub
<#15097 (reply in thread)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ARP33XTDU5LJ5IUVZ7EJ6ID2BSO37AVCNFSM6AAAAABSEM6FT2VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMZSGM4TKMY>
.
You are receiving this because you commented.Message ID:
***@***.***
com>
|
Beta Was this translation helpful? Give feedback.
-
I have created a survey that we want to use to get feedback from users that have been using the GenAI feature for at least 1 week. The feedback will be very helpful in understanding users use cases and how the feature can be improved. The survey is anonymous: https://docs.google.com/forms/d/e/1FAIpQLSehVvK6oVKzikuKzwlIGz2eiaUwhYQq24ZWy9Iqe5NWSrI2Aw/viewform |
Beta Was this translation helpful? Give feedback.
-
beta-2 is a no go for me, config works with 14 but not beta-1 or beta-2.
Here is what I pulled from the log, I did try both with the new ffmpeg and also tried adding the path for 5.0 as noted, same result. I'll try to keep hunting down the solution but any assistance is appreciated.
|
Beta Was this translation helpful? Give feedback.
-
After updating to Beta 2 on HAOS Frigate keeps restarting after a few mins. No clear errors and/or patterns why its restarting, but everything on Beta 1 was working well. |
Beta Was this translation helpful? Give feedback.
-
I have a config validation error when launching the beta2 (hailo8 related) which prevent frigate from starting:
The
So far I have no clue as to what's wrong 👀 |
Beta Was this translation helpful? Give feedback.
-
PLEASE, just display the calculated minimum value on /system#storage where SHM use is already displayed. I feel like I have had to second guess this several times now and a clear in your face value would be nice. Maybe something like this: /dev/shm (✅ meets calculated minimum 512mb ) or /dev/shm ( |
Beta Was this translation helpful? Give feedback.
-
Something appears to be MASSIVLY wrong with object tracking in beta 2. Debug view on all of my cameras is rapidly filling up with objects essentially ghosts for ALL MOVING tracked objects on all cameras. At first I saw this and through the logo jumping issue was there but it is literally every object the camera has seen persisting. |
Beta Was this translation helpful? Give feedback.
-
when i switched to beta2, i keep seeing lots of these in the logs. I switched back to beta1 and no issues. I have 12 of identical cameras, but only frontyard thows those errors. I use TPU + intel i5-10400
|
Beta Was this translation helpful? Give feedback.
-
A quick little question, this is Beta 2: |
Beta Was this translation helpful? Give feedback.
-
I cannot see notifications tab under settings on my Iphone. I see it on a samsung device. Is this by design or is it just me? |
Beta Was this translation helpful? Give feedback.
-
frigate.api.media Message No recordings found for living_room_cam during the requested time range Edit: The above was from a audio detection 28 days old showing in my explore view but I only have a 14 day retention on detections. When browsing Explore view I quite often find detections that have a Video tab for video that no longer exists (sometimes snapshots with broken images but I THINK that was recently fixed). For the most part this appears to be most often for items that would be classed as Detections not alerts.. The object showing in explore is MUCH older than any of the snapshot, alert or detection time frames. If there is no video to watch and no snapshot retained I don't think the object detection should show in explore anymore? |
Beta Was this translation helpful? Give feedback.
-
I'm missing the audio detections in the explore section. I guess this is the case since I'm running the beta. They do appear as an alert however. This is (all relevant) config I'm using: cameras:
back:
audio:
enabled: true
max_not_heard: 15
min_volume: 1800
listen:
- explosion
- siren
- thunder
record:
enabled: true
retain:
days: 7
mode: all
alerts:
retain:
days: 7
pre_capture: 15
post_capture: 15
detections:
retain:
days: 7
pre_capture: 15
post_capture: 15
snapshots:
enabled: true
bounding_box: true
quality: 100
retain:
default: 180
objects:
bbq_grill: 3
waste_bin: 3
bird: 7
bark: 3
siren: 7
explosion: 7
scream: 7
thunder: 7
zones:
zone_terrace:
coordinates: 1,1,1,0.613,0.595,0.672,0.62,1
inertia: 3
loitering_time: 0
zone_garden:
coordinates:
0.399,0.299,0.445,0.119,0.618,0.133,0.731,0.141,0.883,0.353,0.964,0.461,1,0.54,1,0.606,0.59,0.658,0.616,1,0.192,1,0,1,0,0.597,0.169,0.296,0.217,0.296,0.216,0.32,0.336,0.305,0.219,0.603,0.112,0.992,0.193,0.987,0.282,0.597,0.377,0.305
inertia: 3
loitering_time: 0
zone_shed:
coordinates: 0.169,0.097,0.43,0.025,0.43,0.181,0.401,0.294,0.188,0.321
inertia: 3
loitering_time: 0
zone_fence:
coordinates:
0.73,0.141,0.435,0.118,0.435,0.08,0.437,0.015,0.222,0.057,0.22,0,1,0,1,0.536,0.964,0.458
inertia: 3
loitering_time: 0
zone_garden_path:
coordinates: 0.34,0.3,0.374,0.305,0.35,0.37,0.266,0.631,0.183,1,0.111,1,0.219,0.624
loitering_time: 0
objects:
track:
- person
- cat
- dog
- face
- waste_bin
- bird
- raccoon
- umbrella
- bicycle
- squirrel
- rabbit
- bbq_grill
review:
alerts:
required_zones:
- zone_fence
labels:
- explosion
- person
detections:
required_zones:
- zone_terrace
- zone_garden
- zone_shed
- zone_fence
- zone_garden_path
labels:
- cat
- dog
- person
- scream
- siren
- thunder
- bird
- raccoon
- squirrel
- rabbit
- bicycle # to train model
- waste_bin # to train model Any ideas? |
Beta Was this translation helpful? Give feedback.
-
Trying to dip my toes into openvino and onnx on Intel and got openvino working without issues but hitting some problems with onnx. Here is the detectors section:
Here is how I got the model for onnx in 640x640 format:
The detector loads but eventually spits out this error:
Any thoughts or nudges in the right direction would be very welcomed and thank you! |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
Beta Documentation: https://deploy-preview-13787--frigate-docs.netlify.app/
Images
ghcr.io/blakeblackshear/frigate:0.15.0-beta2
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-standard-arm64
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-tensorrt
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-tensorrt-jp4
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-tensorrt-jp5
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-rk
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-rocm
ghcr.io/blakeblackshear/frigate:0.15.0-beta2-h8l
Changes since Beta 1
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:
frigate.db
fileshm_size
is too low then a warning will be printed in the log stating that it needs to be increased.record
config has been refactored to allow for direct control of how longalerts
anddetections
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.hwaccel
preset they are using (preset-vaapi
may need to now bepreset-intel-qsv-h264
orpreset-intel-qsv-h265
) if camera feeds are not functioning correctly after upgrading. This may need to be adjusted on a per-camera basis. If aqsv
preset is not working properly, you may still need to use apreset-vaapi
or revert to the previous ffmpeg version as described below.path: "5.0"
in yourffmpeg:
config entry. For example:ffmpeg
is no longer part of$PATH
. In most cases this is handled automatically.exec
streams will need to add the full path for ffmpeg which in most cases will be/usr/lib/ffmpeg/7.0/bin/ffmpeg
.bin: ffmpeg
defined, it needs to be removed.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
, androcm
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
Other Backend Changes
This discussion was created from the release 0.15.0 Beta 2.
Beta Was this translation helpful? Give feedback.
All reactions