Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2024-11-21 19:07:46 +01:00
Code Issues Projects Releases Wiki Activity

add docs for yolonas plus models (#14161)

Browse Source 
* add docs for yolonas plus models

* typo
This commit is contained in:
Blake Blackshear 2024-10-05 14:51:05 -05:00 committed by GitHub
parent 21c12d118b
commit 039ab1ccd7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 39 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/docs/plus/first_model.md
View File

@ -5,7 +5,7 @@ title: Requesting your first model
## Step 1: Upload and annotate your images ## Step 1: Upload and annotate your images
Before requesting your first model, you will need to upload at least 10 images to Frigate+. But for the best results, you should provide at least 100 verified images per camera. Keep in mind that varying conditions should be included. You will want images from cloudy days, sunny days, dawn, dusk, and night. Refer to the [integration docs](../integrations/plus.md#generate-an-api-key) for instructions on how to easily submit images to Frigate+ directly from Frigate. Before requesting your first model, you will need to upload and verify at least 1 image to Frigate+. The more images you upload, annotate, and verify the better your results will be. Most users start to see very good results once they have at least 100 verified images per camera. Keep in mind that varying conditions should be included. You will want images from cloudy days, sunny days, dawn, dusk, and night. Refer to the [integration docs](../integrations/plus.md#generate-an-api-key) for instructions on how to easily submit images to Frigate+ directly from Frigate.
It is recommended to submit **both** true positives and false positives. This will help the model differentiate between what is and isn't correct. You should aim for a target of 80% true positive submissions and 20% false positives across all of your images. If you are experiencing false positives in a specific area, submitting true positives for any object type near that area in similar lighting conditions will help teach the model what that area looks like when no objects are present. It is recommended to submit **both** true positives and false positives. This will help the model differentiate between what is and isn't correct. You should aim for a target of 80% true positive submissions and 20% false positives across all of your images. If you are experiencing false positives in a specific area, submitting true positives for any object type near that area in similar lighting conditions will help teach the model what that area looks like when no objects are present.
@ -13,7 +13,7 @@ For more detailed recommendations, you can refer to the docs on [improving your
## Step 2: Submit a model request ## Step 2: Submit a model request
Once you have an initial set of verified images, you can request a model on the Models page. Each model request requires 1 of the 12 trainings that you receive with your annual subscription. This model will support all [label types available](./index.md#available-label-types) even if you do not submit any examples for those labels. Model creation can take up to 36 hours. Once you have an initial set of verified images, you can request a model on the Models page. For guidance on choosing a model type, refer to [this part of the documentation](./index.md#available-model-types). Each model request requires 1 of the 12 trainings that you receive with your annual subscription. This model will support all [label types available](./index.md#available-label-types) even if you do not submit any examples for those labels. Model creation can take up to 36 hours.
![Plus Models Page](/img/plus/plus-models.jpg) ![Plus Models Page](/img/plus/plus-models.jpg)
## Step 3: Set your model id in the config ## Step 3: Set your model id in the config

31
docs/docs/plus/improving_model.md
View File

@ -3,7 +3,7 @@ id: improving_model
title: Improving your model title: Improving your model
--- ---
You may find that Frigate+ models result in more false positives initially, but by submitting true and false positives, the model will improve. Because a limited number of users submitted images to Frigate+ prior to this launch, you may need to submit several hundred images per camera to see good results. With all the new images now being submitted, future base models will improve as more and more users (including you) submit examples to Frigate+. Note that only verified images will be used when training your model. Submitting an image from Frigate as a true or false positive will not verify the image. You still must verify the image in Frigate+ in order for it to be used in training. You may find that Frigate+ models result in more false positives initially, but by submitting true and false positives, the model will improve. With all the new images now being submitted by subscribers, future base models will improve as more and more examples are incorporated. Note that only images with at least one verified label will be used when training your model. Submitting an image from Frigate as a true or false positive will not verify the image. You still must verify the image in Frigate+ in order for it to be used in training.
- **Submit both true positives and false positives**. This will help the model differentiate between what is and isn't correct. You should aim for a target of 80% true positive submissions and 20% false positives across all of your images. If you are experiencing false positives in a specific area, submitting true positives for any object type near that area in similar lighting conditions will help teach the model what that area looks like when no objects are present. - **Submit both true positives and false positives**. This will help the model differentiate between what is and isn't correct. You should aim for a target of 80% true positive submissions and 20% false positives across all of your images. If you are experiencing false positives in a specific area, submitting true positives for any object type near that area in similar lighting conditions will help teach the model what that area looks like when no objects are present.
- **Lower your thresholds a little in order to generate more false/true positives near the threshold value**. For example, if you have some false positives that are scoring at 68% and some true positives scoring at 72%, you can try lowering your threshold to 65% and submitting both true and false positives within that range. This will help the model learn and widen the gap between true and false positive scores. - **Lower your thresholds a little in order to generate more false/true positives near the threshold value**. For example, if you have some false positives that are scoring at 68% and some true positives scoring at 72%, you can try lowering your threshold to 65% and submitting both true and false positives within that range. This will help the model learn and widen the gap between true and false positive scores.
@ -36,18 +36,17 @@ Misidentified objects should have a correct label added. For example, if a perso
## Shortcuts for a faster workflow ## Shortcuts for a faster workflow
|Shortcut Key|Description| | Shortcut Key | Description |
|-----|--------| | ----------------- | ----------------------------- |
|`?`|Show all keyboard shortcuts| | `?` | Show all keyboard shortcuts |
|`w`|Add box| | `w` | Add box |
|`d`|Toggle difficult| | `d` | Toggle difficult |
|`s`|Switch to the next label| | `s` | Switch to the next label |
|`tab`|Select next largest box| | `tab` | Select next largest box |
|`del`|Delete current box| | `del` | Delete current box |
|`esc`|Deselect/Cancel| | `esc` | Deselect/Cancel |
|`← ↑ → ↓`|Move box| | `← ↑ → ↓` | Move box |
|`Shift + ← ↑ → ↓`|Resize box| | `Shift + ← ↑ → ↓` | Resize box |
|`-`|Zoom out| | `scrollwheel` | Zoom in/out |
|`=`|Zoom in| | `f` | Hide/show all but current box |
|`f`|Hide/show all but current box| | `spacebar` | Verify and save |
|`spacebar`|Verify and save|

25
docs/docs/plus/index.md
View File

@ -15,17 +15,36 @@ With a subscription, 12 model trainings per year are included. If you cancel you
Information on how to integrate Frigate+ with Frigate can be found in the [integration docs](../integrations/plus.md). Information on how to integrate Frigate+ with Frigate can be found in the [integration docs](../integrations/plus.md).
## Available model types
There are two model types offered in Frigate+: `mobiledet` and `yolonas`. Both of these models are object detection models and are trained to detect the same set of labels [listed below](#available-label-types).
Not all model types are supported by all detectors, so it's important to choose a model type to match your detector as shown in the table under [supported detector types](#supported-detector-types).
| Model Type | Description |
| ----------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| `mobiledet` | Based on the same architecture as the default model included with Frigate. Runs on Google Coral devices and CPUs. |
| `yolonas` | A newer architecture that offers slightly higher accuracy and improved detection of small objects. Runs on Intel, NVidia GPUs, and AMD GPUs. |
## Supported detector types ## Supported detector types
Currently, Frigate+ models support CPU (`cpu`), Google Coral (`edgetpu`), OpenVino (`openvino`), ONNX (`onnx`), and ROCm (`rocm`) detectors.
:::warning :::warning
Frigate+ models are not supported for TensorRT or OpenVino yet. Using Frigate+ models with `onnx` and `rocm` is only available with Frigate 0.15, which is still under development.
::: :::
Currently, Frigate+ models only support CPU (`cpu`) and Coral (`edgetpu`) models. OpenVino is next in line to gain support. | Hardware | Recommended Detector Type | Recommended Model Type |
| ---------------------------------------------------------------------------------------------------------------------------- | ------------------------- | ---------------------- |
| [CPU](/configuration/object_detectors.md#cpu-detector-not-recommended) | `cpu` | `mobiledet` |
| [Coral (all form factors)](/configuration/object_detectors.md#edge-tpu-detector) | `edgetpu` | `mobiledet` |
| [Intel](/configuration/object_detectors.md#openvino-detector) | `openvino` | `yolonas` |
| [NVidia GPU](https://deploy-preview-13787--frigate-docs.netlify.app/configuration/object_detectors#onnx)\* | `onnx` | `yolonas` |
| [AMD ROCm GPU](https://deploy-preview-13787--frigate-docs.netlify.app/configuration/object_detectors#amdrocm-gpu-detector)\* | `rocm` | `yolonas` |
The models are created using the same MobileDet architecture as the default model. Additional architectures will be added in future releases as needed. _\* Requires Frigate 0.15_
## Available label types ## Available label types