@ -85,7 +85,7 @@ After installing the runtime, you need to plug in your Coral Edge TPU into a USB
To use the Edge TPU, you need to convert your model into a compatible format. It is recommended that you run export on Google Colab, x86_64 Linux machine, using the official [Ultralytics Docker container](docker-quickstart.md), or using [Ultralytics HUB](../hub/quickstart.md), since the Edge TPU compiler is not available on ARM. See the [Export Mode](../modes/export.md) for the available arguments.
To use the Edge TPU, you need to convert your model into a compatible format. It is recommended that you run export on Google Colab, x86_64 Linux machine, using the official [Ultralytics Docker container](docker-quickstart.md), or using [Ultralytics HUB](../hub/quickstart.md), since the Edge TPU compiler is not available on ARM. See the [Export Mode](../modes/export.md) for the available arguments.
!!! note "Exporting the model"
!!! example "Exporting the model"
=== "Python"
=== "Python"
@ -105,13 +105,27 @@ To use the Edge TPU, you need to convert your model into a compatible format. It
yolo export model=path/to/model.pt format=edgetpu # Export an official model or custom model
yolo export model=path/to/model.pt format=edgetpu # Export an official model or custom model
```
```
The exported model will be saved in the `<model_name>_saved_model/` folder with the name `<model_name>_full_integer_quant_edgetpu.tflite`.
The exported model will be saved in the `<model_name>_saved_model/` folder with the name `<model_name>_full_integer_quant_edgetpu.tflite`. It is important that your model ends with the suffix `_edgetpu.tflite`, otherwise ultralytics doesn't know that you're using a Edge TPU model.
## Running the model
## Running the model
After exporting your model, you can run inference with it using the following code:
Before you can actually run the model, you will need to install the correct libraries.
!!! note "Running the model"
If `tensorflow` is installed, uninstall tensorflow with the following command:
```bash
pip uninstall tensorflow tensorflow-aarch64
```
Then install/update `tflite-runtime`:
```bash
pip install -U tflite-runtime
```
Now you can run inference using the following code:
!!! example "Running the model"
=== "Python"
=== "Python"
@ -119,7 +133,7 @@ After exporting your model, you can run inference with it using the following co
from ultralytics import YOLO
from ultralytics import YOLO
# Load a model
# Load a model
model = YOLO("path/to/edgetpu_model.tflite") # Load an official model or custom model
model = YOLO("path/to/<model_name>_full_integer_quant_edgetpu.tflite") # Load an official model or custom model
# Run Prediction
# Run Prediction
model.predict("path/to/source.png")
model.predict("path/to/source.png")
@ -128,27 +142,30 @@ After exporting your model, you can run inference with it using the following co
=== "CLI"
=== "CLI"
```bash
```bash
yolo predict model=path/to/edgetpu_model.tflite source=path/to/source.png # Load an official model or custom model
yolo predict model=path/to/<model_name>_full_integer_quant_edgetpu.tflite source=path/to/source.png # Load an official model or custom model
```
```
Find comprehensive information on the [Predict](../modes/predict.md) page for full prediction mode details.
Find comprehensive information on the [Predict](../modes/predict.md) page for full prediction mode details.
???+ warning "Important"
!!! note "Inference with multiple Edge TPUs"
You should run the model using `tflite-runtime` and not `tensorflow`.
If you have multiple Edge TPUs you can use the following code to select a specific TPU.
If `tensorflow` is installed, uninstall tensorflow with the following command:
```bash
=== "Python"
pip uninstall tensorflow tensorflow-aarch64
```
```python
from ultralytics import YOLO
Then install/update `tflite-runtime`:
# Load a model
model = YOLO("path/to/<model_name>_full_integer_quant_edgetpu.tflite") # Load an official model or custom model
```
# Run Prediction
pip install -U tflite-runtime
model.predict("path/to/source.png") # Inference defaults to the first TPU
```
model.predict("path/to/source.png", device="tpu:0") # Select the first TPU
If you want a `tflite-runtime` wheel for `tensorflow` 2.15.0 download it from [here](https://github.com/feranick/TFlite-builds/releases) and install it using `pip` or your package manager of choice.
model.predict("path/to/source.png", device="tpu:1") # Select the second TPU
Each badge shows the status of the last run of the corresponding CI test on the `main` branch of the respective repository. If a test fails, the badge will display a "failing" status, and if it passes, it will display a "passing" status.
Each badge shows the status of the last run of the corresponding CI test on the `main` branch of the respective repository. If a test fails, the badge will display a "failing" status, and if it passes, it will display a "passing" status.
@ -320,7 +320,7 @@ This approach provides a powerful means of customizing state-of-the-art object d
## Citations and Acknowledgements
## Citations and Acknowledgements
We extend our gratitude to the [Tencent AILab Computer Vision Center](https://ai.tencent.com/) for their pioneering work in real-time open-vocabulary object detection with YOLO-World:
We extend our gratitude to the [Tencent AILab Computer Vision Center](https://www.tencent.com/) for their pioneering work in real-time open-vocabulary object detection with YOLO-World:
Welcome to the Ultralytics' <ahref="https://github.com/ultralytics/yolov5">YOLOv5</a>🚀 Documentation! YOLOv5, the fifth iteration of the revolutionary "You Only Look Once" [object detection](https://www.ultralytics.com/glossary/object-detection) model, is designed to deliver high-speed, high-accuracy results in real-time.
Welcome to the Ultralytics' <ahref="https://github.com/ultralytics/yolov5">YOLOv5</a>🚀 Documentation! YOLOv5, the fifth iteration of the revolutionary "You Only Look Once" <ahref="https://www.ultralytics.com/glossary/object-detection">object detection</a> model, is designed to deliver high-speed, high-accuracy results in real-time.
<br><br>
<br><br>
Built on PyTorch, this powerful [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) framework has garnered immense popularity for its versatility, ease of use, and high performance. Our documentation guides you through the installation process, explains the architectural nuances of the model, showcases various use-cases, and provides a series of detailed tutorials. These resources will help you harness the full potential of YOLOv5 for your [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) projects. Let's get started!
Built on PyTorch, this powerful <ahref="https://www.ultralytics.com/glossary/deep-learning-dl">deep learning</a> framework has garnered immense popularity for its versatility, ease of use, and high performance. Our documentation guides you through the installation process, explains the architectural nuances of the model, showcases various use-cases, and provides a series of detailed tutorials. These resources will help you harness the full potential of YOLOv5 for your <ahref="https://www.ultralytics.com/glossary/computer-vision-cv">computer vision</a> projects. Let's get started!
Burhan
4 months ago
committed by
GitHub