Sin descripción

Alexander Freytag ff55002afa support of filelists with relative filenames hace 9 años
.gitignore 943926a51a first commit, supports loading of networks, image preparation, feat extraction for single image hace 10 años
README.md d089a282f2 added small readme hace 9 años
caffe_features_multiple_images.m ff55002afa support of filelists with relative filenames hace 9 años
caffe_features_single_image.m 76f292a096 safety check for normalization, no division by zero hace 9 años
caffe_load_network.m 9b6c843a8d adaptation towards recent caffe layout, made location globally known hace 9 años
caffe_prepare_image.m 943926a51a first commit, supports loading of networks, image preparation, feat extraction for single image hace 10 años
getFieldWithDefault.m c21c1976ce feature extraction supports bilinear pooling and logm transformation hace 10 años
initWorkspaceCaffeTools.m 4072de12c2 minor adaptation in init script hace 9 años

README.md

Summary

A small wrapper library to extract activations of deep neural networks using the popular Caffe toolbox.

Requirements / Dependencies

  • A compiled version of Caffe, tested with 2016-08-20 (hash 14643685a4 )
  • The source code was developed in Matlab 8.2

Installation

  • setup required paths and 3rd-party dependencies via initWorkspaceCaffeTools.m (if caffe is not found on your system, a possible code mirror is suggested)

Common errors

  • Do not forget to add caffe's dependencies (e.g., cuda, gflgs, protobuf, leveldb, lmdb, and mkl) to your LD_LIBRARY_PATH and PATH variable before starting Matlab