Deep Learning Resources

Neural Networks and Deep Learning Model Zoo

A collection of standalone TensorFlow and PyTorch models in Jupyter Notebooks

Python 3.6

Classifiers

• Perceptron [TensorFlow] [PyTorch]

• Logistic Regression [TensorFlow] [PyTorch]

• Softmax Regression (Multinomial Logistic Regression) [TensorFlow][PyTorch]

• Multilayer Perceptron [TensorFlow] [PyTorch]

• Multilayer Perceptron with Dropout [TensorFlow] [PyTorch]

• Multilayer Perceptron with Batch Normalization [TensorFlow] [PyTorch]

• Multilayer Perceptron with Backpropagation from Scratch [TensorFlow]

Convolutional Classifiers

• Convolutional Neural Network [TensorFlow] [PyTorch]

• Convolutional Neural Network with He Initialization [PyTorch]

• Convolutional Neural Network VGG-16 [TensorFlow] [PyTorch]

• Convolutional ResNet and Residual Blocks [PyTorch]

Metric Learning

• Siamese Network with Multilayer Perceptrons [TensorFlow]

Autoencoders

• Autoencoder [TensorFlow] [PyTorch]

• Convolutional Autoencoder with Deconvolutions [TensorFlow] [PyTorch]

• Convolutional Autoencoder with Deconvolutions (without pooling operations) [PyTorch]

• Convolutional Autoencoder with Nearest-neighbor Interpolation [TensorFlow] [PyTorch]

• Convolutional Autoencoder with Nearest-neighbor Interpolation – Trained on CelebA [PyTorch]

• Variational Autoencoder [PyTorch]

General Adversarial Networks

• General Adversarial Networks [TensorFlow]

• Convolutional General Adversarial Networks [TensorFlow]

Tips and Tricks

• Cyclic Learning Rate [PyTorch]

PyTorch Workflows

• Using PyTorch Dataset Loading Utilities for Custom Datasets – CSV files converted to HDF5

• Using PyTorch Dataset Loading Utilities for Custom Datasets – Face Images from CelebA

• Getting Gradients of an Intermediate Variable in PyTorch

TensorFlow Workflows

• Saving and Loading Trained Models – from TensorFlow Checkpoint Files and NumPy NPZ Archives

• Chunking an Image Dataset for Minibatch Training using NumPy NPZ Archives

• Storing an Image Dataset for Minibatch Training using HDF5

• Using Input Pipelines to Read Data from TFRecords Files

• Using Queue Runners to Feed Images Directly from Disk

• Using TensorFlow’s Dataset API

Visual Neural Network

http://scs.ryerson.ca/~aharley/vis/conv/flat.htmlscs.ryerson.ca

Tensorflow — Neural Network Playground