• Training
  • Training Tutorials
  • Training Notebooks


Training Tutorials

We have prepared several Jupyter notebook tutorials to show how to train neural networks. All of them are stored in depthai-ml-training repository. The easiest way to use all the Jupyter notebooks in this repository is by using Google Colaboratory. Google Colaboratory allows you to train neural models yourself using their fast GPU instances and, in some cases (depending on the dependencies of the training frameworks), even using the Google TPU. Alternatively, you can run these Jupyter notebooks on your device.

Training Notebooks

Our training notebooks conver the following computer vision tasks:


Image classification is the task of assigning a predefined label or category to an entire input image.

Object detection

Object detection involves identifying and locating multiple objects within an image and providing bounding boxes around them.

Semantic segmentation

Semantic segmentation aims to classify each pixel in an image into specific classes or categories, effectively assigning a label to every pixel.