This makes you familiar with the training/testing pipeline.

• Training a state-of-the-art classifier on the SVHN dataset (64-bit only)

You can also check these demos while working with tutorials:

• Libidx: simple demo
• MNIST handwritten character classification
• Face detector demo
• Regression demo

EBLearn structure

(No C++ programming needed)

By the end of these series of tutorials, you will learn how to build a classifier in EBLearn. That means that you can build face detectors, handwriting recognition systems, etc. The possibilities are unlimited . I recommend that you go through these tutorials in order, so that you do not need to come back a tutorial if you dont understand something.

• Tutorial 1: Making your dataset from images
• Tutorial 2: Training a digit classifier
• Tutorial 3: Creating an end-to-end face detector
• Tutorial 4: Face detector on a webcam

• Overall library structure
• Libidx Tutorial: a powerful self-contained tensor library.
• Libeblearn Tutorial: an energy-based learning library.
• idx/idxgui Tutorial: a simple demo of how to use image and gui operations.
• Tools: tools for training, detection, data extraction, etc.
• Dataset extraction
• Dataset conversion
• Writing a custom Answer module
• Bootstrapping of negative class for detection
• High-level debugging
• Permuting weights order

Note: A general advice when things don't go as expected is to use the “_debug” version of the corresponding tool. For example, detect_debug rather than detect will give a good feedback of what is happening.