VGG Computer Vision Practicals - Visual Recognition and Machine Learning Summer School, Paris 2013


Planning your laboratory experience

Practicals are organised in tracks of different duration.

  • Fast track: 1.5 hours.
  • Full track: 3 hours.
Parts that should be skipped on fast track are clearly marked [in this style].The practical requires each student to have the following equipment and software:
  • Windows, Mac OS X, or Linux computer
  • At least 2GB RAM
  • MATLAB 2009B onwards (earlier versions may or may not work)
  • MATLAB Image Processing toolbox
Note: If you plan to use students' personal computers, we suggest that you leave plenty of time in advance of the practical in order to download and install the required data and software.


Each practical contains data and MATLAB code (including a copy of the VLFeat library). To install a practical:
  • Find the practical download link at the top of each practical page. E.g. practical-instance-recognition-2013a.tar.gz.
  • Download the package. 
  • Unpack the package. The archive is in .tar.gz format and will unpack to a directory of the same name, e.g. practical-instance-recognition-2013a/.

For convenience, additional packages containing only the code and the data are provided as well; unpack both of them in the same location.

Help and troubleshooting

  • Getting help. As you progress in a practical you can use MATLAB help command to display the help of the MATLAB functions that you need to use. For example, try typing help setup.
  • Interfering VLFeat copies. If you have a copy VLFeat toolbox loaded automatically on starting MATLAB, the copy shipped with this practical may conflict with it (it will generate errors during the execution of the exercises). In this case, switch to the shipped version of the toolbox. First, try issuing clear mex ; vlfeat/toolbox/vl_setup. If this does not solve the problem, exit MATLAB and restart it without loading your default VLFeat installation (this may require editing your MATLAB startup.m file).
  • Corrupted .MAT or other files. If MATLAB complains about a corrupted .mat file, consider trying a different unpacking software. At least one version on WinZip caused problems for some students.

Texte d'origine