Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
Following instructions @ http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html
1) Git cloning @ https://github.com/alexgkendall/caffe-segnet
-- conda new env create
2) proceed to caffe installation @ http://caffe.berkeleyvision.org/installation.html
-- NO change to Makefile.config
-- corrected path to cuda
-- OMG!! Its installing perfectly fine now without any errors yet!
-- make all successful
-- heading towards make test
-- make test success! Awesome
--make runtest ... Success -- 2 disabled tests :|
3) Test run a program
3.2) Pre-req
-- pycaffe dowsnt work now
-- git clone @ https://github.com/alexgkendall/SegNet-Tutorial
-- edit vim Models/segnet_train.prototxt && vim Models/segnet_inference.prototxt
changed data source and batch size
same for segnet basic
-- home path [/home/rise/Vishruit/soft/SegNet-Tutorial]
-- Done
3.2) Running the test program
-- Command --> ./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_solver.prototxt # This will begin training SegNet on GPU 0
./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_solver.prototxt # This will begin training SegNet on GPU 0
./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_basic_solver.prototxt # This will begin training SegNet-Basic on GPU 0
./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_solver.prototxt -weights /SegNet/Models/VGG_ILSVRC_16_layers.caffemodel # This will begin training SegNet on GPU 0 with a pretrained encoder
3.3) Made pycaffe
-- install all the dependencies. Make sure of that!
-- success
-- issue with $PYTHONPATH - automatically gets reset to no value
4) Preparing dataset
-- need to figure out the age old issue of doubling size upon conversion problem
-- shall go ahead with .png format [test TODO]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment