Caffe: a fast open framework for deep learning.
An adapted version of the original caffe deep learning library to support training, finetuning and testing of convolutional neural networks with limited numerical precision of weights and activations
Static version of Caffe known to work with Distributed Deep Q Learning project
Caffe version of code for our paper "Joint unsupervised learning of deep representations and image clusters"
Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.
A caffe version implementation of a hash network(DNNH/NINH) for similarity-based visual research based on paper: Simultaneous feature learning and hash coding with deep neural networks
A modified version of Caffe with memory optimization and metal implementation