Caffe Model Support

Caffe is a popular framework maintained by BVLC at UC Berkeley. It is widely used by computer vision communities, and aims at fast computation and easy usage without any programming. The BVLC team provides trained reference models in their Model Zoo, which can reduce training time required for a new task.


Chainer can import the reference models and emulate the network by Link implementations. This functionality is provided by the chainer.links.caffe.CaffeFunction class.

chainer.links.caffe.CaffeFunction Caffe emulator based on the model file of Caffe.


Chainer can export a model from Link.

chainer.exporters.caffe.export (Experimental) Export a computational graph as Caffe format.