Dataset augmentation
Performance bad and you don’t have enough data?
If you’ve trained a model on your data and performance is poor, it may be that you don’t have enough data. How much is enough? This is hard to say and varies depending on the domain and task.
In this video we look at some options for increasing the size of your dataset, including augmentation, which multiples the training images without needing more annotations. In the following video we will look at using synthetic data to do this.
Experimental Design for Machine Learning
Reach your personal and professional goals
Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.
Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.
