summaries

labml_nn/capsule_networks/__init__.py

@@ -1,8 +1,19 @@
 """
+---
+title: Capsule Networks
+summary: >
+  PyTorch implementation/tutorial of Capsule Networks.
+  Capsule networks is neural network architecture that embeds features
+  as capsules and routes them with a voting mechanism to next layer of capsules.
+---
+
 # Capsule Networks
 
 This is an implementation of [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829).
 
+Capsule networks is neural network architecture that embeds features as capsules and routes them
+with a voting mechanism to next layer of capsules.
+
 Unlike in other implementations of models, we've included a sample, because
 it is difficult to understand some of the concepts with just the modules.
 [This is the annotated code for a model that use capsules to classify MNIST dataset](mnist.html)

labml_nn/capsule_networks/mnist.py

@@ -1,4 +1,9 @@
 """
+---
+title: Classify MNIST digits with Capsule Networks
+summary: Code for training Capsule Networks on MNIST dataset
+---
+
 # Classify MNIST digits with Capsule Networks
 
 This paper implements the experiment described in paper

labml_nn/gan/__init__.py

@@ -1,4 +1,9 @@
 """
+---
+title: Generative Adversarial Networks (GAN)
+summary: A simple PyTorch implementation/tutorial of Generative Adversarial Networks (GAN) loss functions.
+---
+
 # Generative Adversarial Networks (GAN)
 
 This is an implementation of

labml_nn/gan/cycle_gan.py

@@ -1,4 +1,11 @@
 """
+---
+title: Cycle GAN
+summary: >
+  A simple PyTorch implementation/tutorial of Cycle GAN introduced in paper
+  Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks.
+---
+
 # Cycle GAN
 
 This is an implementation of paper

labml_nn/gan/dcgan.py

@@ -1,4 +1,9 @@
 """
+---
+title: Deep Convolutional Generative Adversarial Networks (DCGAN)
+summary: A simple PyTorch implementation/tutorial of Deep Convolutional Generative Adversarial Networks (DCGAN).
+---
+
 # Deep Convolutional Generative Adversarial Networks (DCGAN)
 
 This is an implementation of paper

labml_nn/gan/simple_mnist_experiment.py

@@ -1,4 +1,9 @@
 """
+---
+title: Generative Adversarial Networks experiment with MNIST
+summary: This experiment generates MNIST images using multi-layer perceptron.
+---
+
 # Generative Adversarial Networks experiment with MNIST
 """
 

labml_nn/lstm/__init__.py

@@ -1,4 +1,9 @@
 """
+---
+title: Long Short-Term Memory (LSTM)
+summary: A simple PyTorch implementation/tutorial of Long Short-Term Memory (LSTM) modules.
+---
+
 # Long Short-Term Memory (LSTM)
 """
 

labml_nn/optimizers/__init__.py

@@ -1,4 +1,11 @@
 """
+---
+title: Optimizers
+summary: >
+ A set of PyTorch implementations/tutorials of popular gradient descent based optimizers.
+ Currently includes Adam, AMSGrad and RAdam optimizers.
+---
+
 # Optimizers
 
 ## Optimizer Implementations

labml_nn/optimizers/ada_belief.py

@@ -1,4 +1,9 @@
 """
+---
+title: AdaBelief optimizer
+summary: A simple PyTorch implementation/tutorial of AdaBelief optimizer.
+---
+
 This is based from AdaBelief official implementation
 https://github.com/juntang-zhuang/Adabelief-Optimizer
 """

labml_nn/optimizers/adam.py

@@ -1,4 +1,9 @@
 """
+---
+title: Adam Optimizer
+summary: A simple PyTorch implementation/tutorial of Adam optimizer
+---
+
 # Adam Optimizer
 
 This is an implementation of popular optimizer *Adam* from paper

labml_nn/optimizers/adam_warmup.py

@@ -1,3 +1,10 @@
+"""
+---
+title: Adam optimizer with warm-up
+summary: A simple PyTorch implementation/tutorial of Adam optimizer with warm-up.
+---
+"""
+
 from typing import Dict
 
 from labml_nn.optimizers import WeightDecay

labml_nn/optimizers/amsgrad.py

@@ -1,4 +1,9 @@
 """
+---
+title: AMSGrad Optimizer
+summary: A simple PyTorch implementation/tutorial of AMSGrad optimizer.
+---
+
 # AMSGrad
 
 This is an implementation of the paper

labml_nn/optimizers/configs.py

@@ -1,3 +1,10 @@
+"""
+---
+title: Configurable optimizer module
+summary: This implements a configurable module for optimizers.
+---
+"""
+
 from typing import Tuple
 
 import torch

labml_nn/optimizers/mnist_experiment.py

@@ -1,4 +1,9 @@
 """
+---
+title: MNIST example to test the optimizers
+summary: This is a simple MNIST example with a CNN model to test the optimizers.
+---
+
 # MNIST example to test the optimizers
 """
 import torch.nn as nn

labml_nn/optimizers/noam.py

@@ -1,3 +1,11 @@
+"""
+---
+title: Noam optimizer from Attention is All You Need paper
+summary: >
+  This is a tutorial/implementation of Noam optimizer.
+  Noam optimizer has a warm-up period and then an exponentially decaying learning rate.
+---
+"""
 from typing import Dict
 
 from labml_nn.optimizers import WeightDecay

labml_nn/optimizers/performance_test.py

@@ -1,4 +1,9 @@
 """
+---
+title: Test performance of Adam implementations
+summary: This experiment compares performance of Adam implementations.
+---
+
 # Performance testing Adam
 
 ```

labml_nn/optimizers/radam.py

@@ -1,4 +1,9 @@
 """
+---
+title: RAdam optimizer
+summary: A simple PyTorch implementation/tutorial of RAdam optimizer.
+---
+
 Based on https://github.com/LiyuanLucasLiu/RAdam
 """
 

labml_nn/recurrent_highway_networks/__init__.py

@@ -1,4 +1,9 @@
 """
+---
+title: Recurrent Highway Networks
+summary: A simple PyTorch implementation/tutorial of Recurrent Highway Networks.
+---
+
 # Recurrent Highway Networks
 
 This is an implementation of [Recurrent Highway Networks](https://arxiv.org/abs/1607.03474).

labml_nn/rl/__init__.py

@@ -1,5 +1,13 @@
 """
-# RL Algorithms
+---
+title: Reinforcement Learning Algorithms
+summary: >
+  This is a collection of PyTorch implementations/tutorials of reinforcement learning algorithms.
+  It currently includes Proximal Policy Optimization, Generalized Advantage Estimation, and
+  Deep Q Networks.
+---
+
+# Reinforcement Learning Algorithms
 
 * [Proximal Policy Optimization](ppo)
     * [This is an experiment](ppo/experiment.html) that runs a PPO agent on Atari Breakout.

labml_nn/rl/dqn/__init__.py

@@ -1,4 +1,14 @@
 """
+---
+title: Deep Q Networks (DQN)
+summary: >
+  This is a PyTorch implementation/tutorial of Deep Q Networks (DQN) from paper
+  Playing Atari with Deep Reinforcement Learning.
+  This includes dueling network architecture, a prioritized replay buffer and
+  double-Q-network training.
+---
+
+
 # Deep Q Networks (DQN)
 
 This is an implementation of paper

labml_nn/rl/dqn/experiment.py

@@ -1,4 +1,9 @@
 """
+---
+title: DQN Experiment with Atari Breakout
+summary: Implementation of DQN experiment with Atari Breakout
+---
+
 # DQN Experiment with Atari Breakout
 
 This experiment trains a Deep Q Network (DQN) to play Atari Breakout game on OpenAI Gym.

labml_nn/rl/dqn/model.py

@@ -1,4 +1,9 @@
 """
+---
+title: Deep Q Network (DQN) Model
+summary: Implementation of neural network model for Deep Q Network (DQN).
+---
+
 # Deep Q Network (DQN) Model
 """
 

labml_nn/rl/dqn/replay_buffer.py

@@ -1,4 +1,9 @@
 """
+---
+title: Prioritized Experience Replay Buffer
+summary: Annotated implementation of prioritized experience replay using a binary segment tree.
+---
+
 # Prioritized Experience Replay Buffer
 
 This implements paper [Prioritized experience replay](https://arxiv.org/abs/1511.05952),

labml_nn/rl/game.py

@@ -1,4 +1,9 @@
 """
+---
+title: Atari wrapper with multi-processing
+summary: This implements the Atari games with multi-processing.
+---
+
 # Atari wrapper with multi-processing
 """
 import multiprocessing

labml_nn/rl/ppo/__init__.py

@@ -1,4 +1,10 @@
 """
+---
+title: Proximal Policy Optimization (PPO)
+summary: >
+ An annotated implementation of Proximal Policy Optimization (PPO) algorithm in PyTorch.
+---
+
 # Proximal Policy Optimization (PPO)
 
 This is a an implementation of [Proximal Policy Optimization - PPO](https://arxiv.org/abs/1707.06347).

labml_nn/rl/ppo/experiment.py

@@ -1,4 +1,9 @@
 """
+---
+title: PPO Experiment with Atari Breakout
+summary: Annotated implementation to train a PPO agent on Atari Breakout game.
+---
+
 # PPO Experiment with Atari Breakout
 
 This experiment trains Proximal Policy Optimization (PPO) agent  Atari Breakout game on OpenAI Gym.

labml_nn/rl/ppo/gae.py

@@ -1,4 +1,9 @@
 """
+---
+title: Generalized Advantage Estimation (GAE)
+summary: A PyTorch implementation/tutorial of Generalized Advantage Estimation (GAE).
+---
+
 # Generalized Advantage Estimation (GAE)
 
 This is an implementation of paper [Generalized Advantage Estimation](https://arxiv.org/abs/1506.02438).

labml_nn/sketch_rnn/__init__.py

@@ -1,4 +1,11 @@
 """
+---
+title: Sketch RNN
+summary: >
+  This is an annotated PyTorch implementation of the Sketch RNN from paper A Neural Representation of Sketch Drawings.
+  Sketch RNN is a sequence-to-sequence model that generates sketches of objects such as bicycles, cats, etc.
+---
+
 # Sketch RNN
 
 This is an annotated implementation of the paper