Research Project

user:  ssh -X uni@robotvision1.cs.adelaide.edu.au pass: same as local machine admin: @robotvision1.cs.adelaide.edu.au install python3.5.2 https://tecadmin.net/install-python-3-5-on-ubuntu/

1. Detect to Track and Track to Detect_ICCV2017_Christoph Feichtenhofer et al. (code available) project page:  http://www.robots.ox.ac.uk/~vgg/research/detect-track/ 1> Summary: (1) T he input to the network consists of multiple frames which are first passed through a ConvNet trunk to produce convolutional features which are shared for the task of detection and tracking. Then compute convolutional cross-correlation between the feature responses of adjacent frames to estimate the local displacement at different feature scales. On top of the features, we employ an RoI-pooling layer to classify and regress box proposals as well as an RoI-tracking layer that regresses box transformations (translation, scale, aspect ratio) across frames. 2> Network structure: Add caption 3>. Some details: (1) Reweighting scores across the detection tubes before putting them to construct the tracking regression. (2) Perform non-maximum suppression with bounding-box voting bef...

reference: http://www.gurobi.com/documentation/7.5/quickstart_linux/software_installation_guid.html (1) add in 'bashrc' export LD_LIBRARY_PATH="${LD_LIBRARY_PATH}:/opt/gurobi751/linux64/lib" (2) temporary sudo ldconfig /opt/gurobi751/linux64/lib (3) permanent Add the gurobi lib path: cd /etc/ld.so.conf.d/ ls  sudo nano gurobi.conf 'paste'   /opt/gurobi751/linux64/lib sudo ldconfig (4) path configuration 1>in /home/.bashrc    add:   export LD_LIBRARY_PATH=/usr/local/cuda-8.0/lib64/ 2>in terminal $ sudo nano /etc/ld.so.conf.d/cuda-8-0.conf    in cuda-8-0.conf: add  /usr/local/cuda-8.0/lib64/ $ sudo ldconfig (5) mnt hard disk: https://help.ubuntu.com/community/InstallingANewHardDrive (6) clear up space in Linux system: https://itsfoss.com/free-up-space-ubuntu-linux/ (7)  conda install cuda8.0 conda install -c soumith cuda80