Python codes for exercises in the official Pytorch tutorials
SEQUENCE MODELS AND LONG-SHORT TERM MEMORY NETWORKS
This program is for the exercise: Augmenting the LSTM part-of-speech tagger with character-level features.
WORD EMBEDDINGS: ENCODING LEXICAL SEMANTICS
This program is for the exercise: Computing Word Embeddings: Continuous Bag-of-Words.
TRANSLATION WITH A SEQUENCE TO SEQUENCE NETWORK AND ATTENTION
This program demonstrates how to train a seq2seq model without attention mechanism.
TRANSLATION WITH A SEQUENCE TO SEQUENCE NETWORK AND ATTENTION
The original program shown in the above link assumes the batch size is one. Apparently, this is not a "real" batch training. The seq2seq_translation_batch_training.py & seq2seq_translation_batch_training.ipynb show how to use batch training.
At the end of this tutorial, the author asked readers to run the code with a harder dataset. I run Resnet with the plant seeding classification dataset. In my code, I show how to add multiple layers to the top of a deep neural network model and how to use pretrained models in a Kaggle kernel.
Two classes, ImageFolderSplitter and DatasetFromFilename, are provided in this file. They work like torchvision.datasets.ImageFolder, but they can split a whole dataset into a training set and a validation set.
A class simulates the height_shift_range and the width_shift_range of ImageDataGenerator in Keras. This class is initialized by two fractions, x and y, representing the fraction of width and the fraction of height, respectively. In addition, this class translates an PIL Image object. It should be used with other transforms in torchvision.
There's a class named RandomAffine in PyTorch can do the similar things. However, after RandomAffine translating an image, black areas (the color is specified by the parameter fillcolor) are left on the image. Unlike RandomAffine, ShiftTransform fills the points outside the boundaries using the points on the boundaries.