forked from microsoft/CNTK
-
Notifications
You must be signed in to change notification settings - Fork 0
Train with a multitask objective
Frank Seide edited this page Aug 27, 2016
·
2 revisions
You can just define your combined criterion as a BrainScript expression and you can monitor all individual task losses by specifying them as evaluationNodes.
task1loss = CrossEntropyWithSoftMax(prediction,label)
task2loss = SquareError(reconstruction,input)
mtloss = task1loss + Constant(0.3) .* task2loss
criterionNodes = (mtloss)
evaluationNodes = (task1loss:task2loss)
Getting Started
Additional Documentation
How to use CNTK
Using CNTK Models in Your Code
- Overview
- Nuget Package for Evaluation
- C++ Evaluation Interface
- C# Evaluation Interface
- Evaluating Hidden Layers
- C# Image Transforms for Evaluation
- C# Multi-model Evaluation
- Evaluate in Azure
Advanced topics
Licenses
Source Code & Development