Marvin is a deep learning framework designed first and foremost to be hackable. It is naively simple for fast prototyping, uses only basic C/C++, and only calls CUDA and cuDNN as dependencies.
S. Levine, P. Pastor, A. Krizhevsky, und D. Quillen. (2016)cite arxiv:1603.02199Comment: This is an extended version of "Learning Hand-Eye Coordination for Robotic Grasping with Large-Scale Data Collection," ISER 2016. Draft modified to correct typo in Algorithm 1 and add a link to the publicly available dataset.
F. Bogo, J. Romero, M. Loper, und M. Black. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Seite 3794--3801. Washington, DC, USA, IEEE Computer Society, (2014)