Intel Advisor's integer-based Roofline chart eases application optimization with visual guidance.
Caffe is a deep learning framework developed by the Berkeley Vision and Learning Center (BVLC) and one of the most popular community frameworks for image recognition. Caffe is often used as a benchmark together with AlexNet*, a neural network topology for image recognition, and ImageNet*, a database of labeled images.
by Henry A. Gabb, Sr. Principal Engineer, Intel Software and Services Group