model_zoo

Model Zoo

A collection of standalone TensorFlow and PyTorch models in Jupyter Notebooks.

Classifiers

• Perceptron [TensorFlow] [PyTorch 0.4]
• Logistic Regression [TensorFlow] [PyTorch 0.4]
• Softmax Regression (Multinomial Logistic Regression) [TensorFlow] [PyTorch 0.4]
• Multilayer Perceptron [TensorFlow] [PyTorch 0.4]
• Multilayer Perceptron with Dropout [TensorFlow] [PyTorch 0.4]
• Multilayer Perceptron with Batch Normalization [TensorFlow] [PyTorch 0.4]
• Multilayer Perceptron with Backpropagation from Scratch [TensorFlow]

Convolutional Classifiers

• Convolutional Neural Network [TensorFlow] [PyTorch 0.4]
• Convolutional Neural Network with He Initialization [TensorFlow] [PyTorch 0.4]
• Convolutional Neural Network VGG-16 [TensorFlow] [PyTorch 0.4]
• Convolutional ResNet and Residual Blocks [PyTorch 0.4]

Metric Learning

• Siamese Network with Multilayer Perceptrons [TensorFlow]

Autoencoders

• Autoencoder [TensorFlow] [PyTorch 0.4]
• Convolutional Autoencoder with Deconvolutions [TensorFlow] [PyTorch 0.4]
• Convolutional Autoencoder with Deconvolutions (without pooling operations) [PyTorch 0.4]
• Convolutional Autoencoder with Nearest-neighbor Interpolation [TensorFlow] [PyTorch 0.4]
• Convolutional Autoencoder with Nearest-neighbor Interpolation -- Trained on CelebA [PyTorch 0.4]
• Variational Autoencoder [PyTorch 0.4]

General Adversarial Networks

• General Adversarial Networks [TensorFlow]
• Convolutional General Adversarial Networks [TensorFlow]

PyTorch 0.4 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