Posted On: Oct 5, 2018
The built-in Image Classification algorithm that comes with Amazon SageMaker now supports additional enhancements. The algorithm now supports multi-label inputs and mixed-precision mode for faster training.
The Image Classification algorithm can now take an image as an input and add multiple labels to that image. This is helpful because most images contain multiple elements and the ability to add multiple labels can produce better and more usable results. As an example, this can be used to detect and classify different elements during medical image processing for better detection and treatment.
The second enhancement for the Image Classification algorithm is to enable mixed-precision mode, consuming less memory while maintaining similar accuracy. With this mode, customers can benefit from faster training and lower costs.