Deep Learning with Your Own Image Dataset

This page shows the overview of how to start deep learning with your own image dataset.

1. Collect raw images

Collect available images from Web or take pictures by yourself.

2. Annotate images

Label each image or each region in the images.

3. Train neural network

Choose one network model according to your task.

There are some training scripts in jsk_perception package.

Training for semantic segmentation

Training for instance segmentation

Training for object detection

4. Infer with trained network

Now you can use your trained network to infer things as a ROS node.

Nodes for semantic segmentation

Nodes for instance segmentation

Nodes for object detection