A Part of the CIM Research Group

Artificial Perception Laboratory

The Artificial Perception Laboratory, a part of the Centre for Intelligent Machines, conducts research activities mainly in topics related to computer vision: data acquisition, image segmentation, view correspondence, model fitting, autonomous exploration of scenes, etc. While based on solid scientific theory, most of the research is heavily tested to prove its practical soundness.

Over the years, the Laboratory has accumulated considerable expertise in the processing and analysis of range images, and developed several specialized software applications. Due to its continuous interaction with world class educational institutions and industries, the Laboratory is on the cutting edge of its field.



Docker workarounds

When running intensive code e.g. pytorch dataloaders, errors may occur in a docker container due to memory limits. You may see errors such as Unable to open shared memory object </torch_3500_2599739126>. To work around them, add –ipc=host to your docker create or run command. An example of a complete command for one of our machines: …

GPU Benchmarking

Some basic numbers for our systems that might be generally useful. Executed using tensorflow-nightly as of April 22, 2019 as a ResNet50 model with the batch size set to 32 or 64 depending what the GPU can fit. Values reported are images/sec. Float type/GPU Quadro P6000 K40 2080 Ti 32 bit float 213 30 300 …

Docker commands

These commands will likely be useful for anyone doing ML and needing to use different libraries and/or not conflict with other users on the same machine. They are targeted towards our lab but may be generally useful. 1. Create container.    Container name is up to you.  To make Nick’s life easier, I recommend adding your …


Prof. Frank Ferrie: 514-398-6042

Main ECE Reception: 514-398-7110