Caffe

Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) and community contributors.

This repo is a modification of my own on Ubuntu18.04LTS + cuda10.0(1080TI) + cuDNN7.6.5 + OpenCV3.4.11

Check out the Official project site for all the details like

• DIY Deep Learning for Vision with Caffe
• Tutorial Documentation
• BAIR reference models and the community model zoo
• Installation instructions

License and Citation

Original version of Caffe is released under the BSD 2-Clause license. The BAIR/BVLC reference models are released for unrestricted use.

I have made and will make some modification or addition in the future for my own uncommercial use of just interests.

Install

See here.

To build, use

make all -j4
make test -j4
make runtest -j4

To build pycaffe, please, make sure to set default python as python3, and install pydot and graphviz:

sudo pip3 install pydot
sudo apt install graphviz

Then, run with:

./makepy.sh
make pytest -j4