CIFAR Challenge!

Instructions

• CIFAR-10 is a small computer vision dataset that was an important benchmark for some of the seminal early work in deep-learning for computer vision.
• Dowload cifar_challenge.py and cifar_test.py
• Read the instructions in cifar_challenge.py

• If you want to take advantage of the gpu-enabled workstations in the JMU CS labs you can connect the lab machine from your VM with port forwarding:

  ssh -L 16006:127.0.0.1:6006 -J <jmuEID>@stu.cs.jmu.edu <jmuEID>@<labcomputer>.cs.jmu.edu 

  Possible lab computers are L25001 trough L25030.

  Now that you are logged into the remote machine, source the preconfigured virtual environent:

  source /cs/shr/cs445/anaconda3_gpu/bin/activate

  Run tensorboard on the lab machine:

  tensorboard --logdir <logs path> --port 6006

  Now can view tensorboard on your local browser at http://localhost:16006

• If you are using your own laptop, you’ll need to install tensorboard:

  conda install -c conda-forge tensorboard