FudanDNN

FudanDNN Toolkit
We introduce a deep learning framework, named FudanDNN, developed by Robot Research Group, at Fudan University. Unlike the above tools, FudanDNN is designed to be used in business environments, rather than as a research tool. It is a C++-based, industry-focused, distributed deep-learning framework with expression, speed, and modularity. FudanDNN neural nets include restricted Boltzmann machines (RBM), autoencoders, convolutional nets, recursive neural nets (LSTMs) and any combination of them, which allows for fast prototyping for non-experts. The most distinctive feature of this tool is its GUI-based designer. By this designer, the structure of deep networks can be easily defined by simple drag-and-drop operations.

Source code can be download from (GitHub FudanDNN)

复旦深度学习开发工具
FudanDNN是由复旦大学计算机学院机器人研究组所开发的一款基于深度学习技术的应用快速开发的工具,其最主要的特色是可以通过图形化界面来配置复杂的网络结构,开发者仅需对深度学习技术有初步的了解就可以使用深度学习技术来设计和开发有关图像、声音和文本处理方面的应用。对于该FudanDNN工具,我们仍然在持续地改进中,如有任何问题,请联系zhengxq@fudan.edu.cn(郑骁庆)。

FudanDNN源代码下载地址:(GitHub FudanDNN)

Comments are closed.