• Git clone and put it into CAFFE_ROOT/examples/;

• Download the fcn-32s-pascalcontext.caffemodel here and move it into CAFFE_ROOT/models/fcn-32s-pascalcontext.caffemodel;

• Download the dataset and put it into CAFFE_ROOT/data/;

• Run CAFFE_ROOT/examples/digits2.0/covert.py for converting data into lmdb;

• Run solve.py to start training.

• Download the pre-trained model or train your own model as mentioned above;
• Run CAFFE_ROOT/examples/digits2.0/test_fcn11_full.m(need Matlab and matcaffe);

Code base on caffe

Contributors: [email protected]