titles

Makefile

@@ -22,7 +22,7 @@ uninstall: ## Uninstall
 	pip uninstall labml_nn
 
 docs: ## Render annotated HTML
-	python ../../pylit/pylit.py --remove_empty_sections -s ../../pylit/pylit_docs.css -t ../../pylit/template_docs.html -d html -w labml_nn
+	python ../../pylit/pylit.py --remove_empty_sections --title_md -s ../../pylit/pylit_docs.css -t ../../pylit/template_docs.html -d html -w labml_nn
 
 pages: ## Copy to lab-ml site
 	@cd ../lab-ml.github.io; git pull

labml_nn/capsule_networks/__init__.py

@@ -1,4 +1,6 @@
 """
+# Capsule Networks
+
 This is an implementation of [Dynamic Routing Between Capsules](https://arxiv.org/abs/1710.09829).
 
 Unlike in other implementations of models, we've included a sample, because

labml_nn/gan/__init__.py

@@ -1,4 +1,6 @@
 """
+# Generative Adversarial Networks (GAN)
+
 This is an implementation of
 [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661).
 

labml_nn/gan/cycle_gan.py

@@ -1,5 +1,6 @@
 """
 # Cycle GAN
+
 This is an implementation of paper
 [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://arxiv.org/abs/1703.10593).
 

labml_nn/gan/dcgan.py

@@ -1,4 +1,6 @@
 """
+# Deep Convolutional Generative Adversarial Networks (DCGAN)
+
 This is an implementation of paper
 [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434).
 

labml_nn/gan/simple_mnist_experiment.py

@@ -1,3 +1,7 @@
+"""
+# Generative Adversarial Networks experiment with MNIST
+"""
+
 from typing import Optional
 
 import torch

labml_nn/lstm/__init__.py

@@ -1,3 +1,7 @@
+"""
+# Long Short-Term Memory (LSTM)
+"""
+
 from typing import Optional, Tuple
 
 import torch

labml_nn/recurrent_highway_networks/__init__.py

@@ -1,4 +1,6 @@
 """
+# Recurrent Highway Networks
+
 This is an implementation of [Recurrent Highway Networks](https://arxiv.org/abs/1607.03474).
 """
 from typing import Optional

labml_nn/rl/ppo/__init__.py

@@ -1,4 +1,6 @@
 """
+# Proximal Policy Optimization (PPO)
+
 This is a an implementation of [Proximal Policy Optimization - PPO](https://arxiv.org/abs/1707.06347).
 
 You can find an experiment that uses it [here](experiment.html).

labml_nn/rl/ppo/experiment.py

@@ -1,4 +1,6 @@
 """
+# PPO Experiment with Atari Breakout
+
 This experiment runs PPO  Atari Breakout game on OpenAI Gym.
 It runs the [game environments on multiple processes](game.html) to sample efficiently.
 """

labml_nn/rl/ppo/gae.py

@@ -1,4 +1,6 @@
 """
+# Generalized Advantage Estimation (GAE)
+
 This is an implementation of paper [Generalized Advantage Estimation](https://arxiv.org/abs/1506.02438).
 """
 

labml_nn/rl/ppo/game.py

@@ -1,3 +1,6 @@
+"""
+# Atari wrapper with multi-processing
+"""
 import multiprocessing
 import multiprocessing.connection
 

labml_nn/transformers/configs.py

@@ -1,3 +1,6 @@
+"""
+# Configurable Transformer Components
+"""
 import copy
 
 import torch.nn as nn

labml_nn/transformers/label_smoothing_loss.py

@@ -1,3 +1,6 @@
+"""
+# Label Smoothing Loss
+"""
 import matplotlib.pyplot as plt
 import numpy as np
 import torch

labml_nn/transformers/models.py

@@ -1,3 +1,6 @@
+"""
+# Transformer Models
+"""
 import math
 
 import torch