Update megadetector.md

megadetector.md

@@ -445,10 +445,10 @@ It's not quite as simple as "these platforms all run MegaDetector on your images
 
 * [FastAPI/Streamlit package for serving MD and visualizing results](https://github.com/abhayolo/megadetector-fastapi)
 * [SpSeg](https://github.com/bhlab/SpSeg/) (pipeline for running MD along with a custom classifier)
-* [MegaDetectorLite](https://github.com/timmh/MegaDetectorLite) is a set of scripts to convert MDv5 into ONNX and TensorRT formats for embedded deployments
-* We developed a [batch processing API](https://github.com/microsoft/CameraTraps/tree/master/api/batch_processing) that runs images on many GPUs at once on Azure.  There is no public instance of this API, but the code allows you to stand up your own endpoint.
-* You can run MegaDetector on images stored in Google Drive using this [Colab notebook](https://github.com/microsoft/CameraTraps/blob/master/detection/megadetector_colab.ipynb) ([open in Colab](https://colab.research.google.com/github/microsoft/CameraTraps/blob/master/detection/megadetector_colab.ipynb)).
+* [MegaDetectorLite](https://github.com/timmh/MegaDetectorLite) is a set of scripts to convert MDv5 into ONNX and TensorRT formats for embedded deployments.
 * [Ben Evans](https://bencevans.io/) made a [pip-installable wrapper](https://github.com/bencevans/camtrapml) for MegaDetector (and other models).
+* We developed a [batch processing API](https://github.com/microsoft/CameraTraps/tree/master/api/batch_processing) that runs images on many GPUs at once on Azure.  There is no public instance of this API, but the code allows you to stand up your own endpoint.
+* We maintain a [Colab notebook](https://github.com/microsoft/CameraTraps/blob/master/detection/megadetector_colab.ipynb) ([open in Colab](https://colab.research.google.com/github/microsoft/CameraTraps/blob/master/detection/megadetector_colab.ipynb)) for running MDv5 on images stored in Google Drive.
 * We provide code for a [real-time MegaDetector API using Flask](https://github.com/microsoft/CameraTraps/tree/main/api/synchronous).  This is deployed via Docker, so the Dockerfile provided for the real-time may be a good starting point for other Docker-based MegaDetector deployments as well.