Torch

Torch is a scientific computing framework for machine learning and deep learning algorithms. It is easy to use with efficient and fast scripting language Lua. Check http://torch.ch/ for more information.

Here are some steps you can follow when getting started with Torch.

1. Install Torch. http://torch.ch/docs/getting-started.html#_
2. Try some hands-on examples. http://torch.ch/docs/five-simple-examples.html#_
3. Go through the deep learning tutorial with Torch. https://github.com/soumith/cvpr2015/blob/master/Deep%20Learning%20with%20Torch.ipynb
4. Read the cheatsheet end-to-end carefully. https://github.com/torch/torch7/wiki/Cheatsheet

Some Useful Links

nngraph: Graphical computation for nn library in Torch. https://github.com/torch/nngraph

hdf5: Read/Write Torch data from/to HDF5 files. https://github.com/deepmind/torch-hdf5

iTorch: An IPython kernel for Torch, with plotting and visualization. https://github.com/facebook/iTorch

dpnn: Deep extensions for nn. https://github.com/Element-Research/dpnn

nninit: Weight initialisation schemes for Torch7 neural network module. https://github.com/Kaixhin/nninit

A clear and readable code for Image Captioning. (you can follow the structure of this code when you start a new project with Torch). https://github.com/karpathy/neuraltalk2

A list of awesome Torch tutorial, projects and communities. https://github.com/carpedm20/awesome-torch

PyTorch

Pytorch is a deep learning framework based on python. It wraps the Torch library and provides several high-level features. Check http://pytorch.org/ for more information.