a DAG CNN Implementation backed on MatConvNet

MatConvNet is a MATLAB toolbox implementing Convolutional Neural Networks (CNNs) for computer vision applications. It is simple, efficient, and can run and learn state-of-the-art CNNs. Several example CNNs are included to classify and encode images. Please visit the homepage to know more.

What'sNew

• DAG We reimplement the network architecture towards a fully DAG topology.
• MultiTask
• concat layer.

A Fast Example

1. copy multitasknn/ to /path/to/Matconvnet/, add this fold into you Matlab path
2. run multitask/exmaple/fast_test_mt_cnn.m