A couple of scripts to illustrate how to do CNNs and RNNs in PyTorch

This is just a couple of simple scripts to illustrate how to use PyTorch. There are two examples:

1) Convolutional residual network (bottleneck variant) inspired by [R1] -- We use CIFAR-10 to train/test.

2) LSTM-based word language model inspired by [R2] -- We use a custom-processed version of the Penn Treebank data set.

[R1] He et al. (2015), "Deep residual learning for image recognition", Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 770-778. https://arxiv.org/abs/1512.03385 
[R2] Zaremba et al. (2015), "Recurrent neural network regularization", Int. Conf. on Learning Representations (ICLR). https://arxiv.org/abs/1409.2329