torch像matlab一样方便,速度基本与caffe在一个量级上。调试torch就是调试脚本语言
torch7都封装好了,直接堆就行了
Yann LeCun: Caffe and Torch serve different purpose. Caffe is strictly a convnet training system that gives you relatively little flexibility. Torch is a whole development environment with a scientific computing back-end and a machine learning library on top. It's much more flexible as a general research tool.
caffe definitely grew in popularity very quickly, and it does a narrow set of tasks very well, but I dont agree that the code is cleaner (in fact I think the opposite), and I dont see the design to be particularly broad-minded (i.e. generic neural networks, or a general scientific computing framework).