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