OverFeat is an image recognizer and feature extractor built around a convolutional network.
The OverFeat convolutional net was trained on the ImageNet 1K dataset. It participated in the ImangeNet Large Scale Recognition Challenge 2013 under the name “OverFeat NYU”.
This release provides C/C++ code to run the network and output class probabilities or feature vectors. It also includes a webcam-based demo.
Lua is a very simple, compact and efficient interpreter/compiler with a straightforward syntax. It is used widely as a scripting language in the computer game industry. Torch extends Lua with an extensive numerical library and various facilities for machine learning and computer vision.
Torch has computational back-ends for multicore/multi-CPU machines (using Intel/AVX and OpenMP), NVidia GPUs (using CUDA), and ARM CPUs (using the Neon instruction set).
Many research projects at the CILVR Lab are built with Torch.