Intermediate release

Tagging the 'master' branch before performing a few API-breaking changes.

v0.3.0

• Supports PyTorch 1.0.1
• Supports installation as a Python package
• Many features (TBD) since release v0.2.0 (PyTorch 0.4)

PyTorch 0.4 support and new features

• PyTorch 0.4 support
• An implementation of Baidu's RNN pruning paper from ICLR 2017
  Narang, Sharan & Diamos, Gregory & Sengupta, Shubho & Elsen, Erich. (2017).
  Exploring Sparsity in Recurrent Neural Networks. (https://arxiv.org/abs/1704.05119)
• Add a word language model pruning example using AGP and Baidu RNN pruning
• Quantization aware training (4-bit quantization)
• New models: pre-activation ResNet for ImageNet and CIFAR, and AlexNet with batch-norm
• New quantization documentation content

Initial version

We're tagging this version which uses PyTorch 0.3, and we want to want to move the 'master' branch to support PyTorch 0.4 and its API changes.