[SYSTEMDS-1676] Add a new 2D softmax layer

• Type: New Feature
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: SystemML 0.15
• Component/s: Algorithms
• Epic Link: Deep Learning DML Library
• Sprint: Sprint 1
• Assignee: Fei Hu
• Reporter: Mike Dusenberry
• Created: 09/Jun/17 20:13
• Updated: 09/Sep/17 05:26
• Resolved: 30/Jun/17 23:38

Description

A 2D softmax layer would accept a tensor of shape (N,C,H,W), where the C axis contains scores for D classes, and output a tensor of the same shape, with the scores transformed to normalized probabilities. The typical use case would be a segmentation problem, in which every pixel has a multiclass prediction.