# Deep Learning Resources

## Neural Networks and Deep Learning Model Zoo

A collection of standalone TensorFlow and PyTorch models in Jupyter Notebooks

![Python 3.6](https://img.shields.io/badge/Python-3.6-blue.svg)

**Classifiers**

* Perceptron \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/perceptron.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/perceptron.ipynb)]
* Logistic Regression \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/logistic-regression.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/logistic-regression.ipynb)]
* Softmax Regression (Multinomial Logistic Regression) \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/softmax-regression.ipynb)]\[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/softmax-regression.ipynb)]
* Multilayer Perceptron \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/multilayer-perceptron.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/multilayer-perceptron.ipynb)]
* Multilayer Perceptron with Dropout \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/multilayer-perceptron-dropout.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/multilayer-perceptron-dropout.ipynb)]
* Multilayer Perceptron with Batch Normalization \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/multilayer-perceptron-batchnorm.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/multilayer-perceptron-batchnorm.ipynb)]
* Multilayer Perceptron with Backpropagation from Scratch \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/multilayer-perceptron-lowlevel.ipynb)]

**Convolutional Classifiers**

* Convolutional Neural Network \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/convnet.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/convnet.ipynb)]
* Convolutional Neural Network with He Initialization \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/convnet-he-init.ipynb)]
* Convolutional Neural Network VGG-16 \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/convnet-vgg16.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/convnet-vgg16.ipynb)]
* Convolutional ResNet and Residual Blocks \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/resnet-ex-1.ipynb)]

**Metric Learning**

* Siamese Network with Multilayer Perceptrons \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/siamese-1.ipynb)]

**Autoencoders**

* Autoencoder \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/autoencoder.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/autoencoder.ipynb)]
* Convolutional Autoencoder with Deconvolutions \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/autoencoder-deconv.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/autoencoder-deconv.ipynb)]
* Convolutional Autoencoder with Deconvolutions (without pooling operations) \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/autoencoder-deconv-2.ipynb)]
* Convolutional Autoencoder with Nearest-neighbor Interpolation \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/autoencoder-conv.ipynb)] \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/autoencoder-conv.ipynb)]
* Convolutional Autoencoder with Nearest-neighbor Interpolation – Trained on CelebA \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/autoencoder-conv-2.ipynb)]
* Variational Autoencoder \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/autoencoder-var.ipynb)]

**General Adversarial Networks**

* General Adversarial Networks \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/gan.ipynb)]
* Convolutional General Adversarial Networks \[[TensorFlow](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/gan-conv.ipynb)]

**Tips and Tricks**

* Cyclic Learning Rate \[[PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/cyclical-learning-rate.ipynb)]

**PyTorch Workflows**

* [Using PyTorch Dataset Loading Utilities for Custom Datasets – CSV files converted to HDF5](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/custom-data-loader-csv.ipynb)
* [Using PyTorch Dataset Loading Utilities for Custom Datasets – Face Images from CelebA](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/custom-data-loader-celeba.ipynb)
* [Getting Gradients of an Intermediate Variable in PyTorch](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/pytorch_ipynb/manual-gradients.ipynb)

**TensorFlow Workflows**

* [Saving and Loading Trained Models – from TensorFlow Checkpoint Files and NumPy NPZ Archives](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/saving-and-reloading-models.ipynb)
* [Chunking an Image Dataset for Minibatch Training using NumPy NPZ Archives](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/image-data-chunking-npz.ipynb)
* [Storing an Image Dataset for Minibatch Training using HDF5](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/image-data-chunking-hdf5.ipynb)
* [Using Input Pipelines to Read Data from TFRecords Files](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/tfrecords.ipynb)
* [Using Queue Runners to Feed Images Directly from Disk](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/file-queues.ipynb)
* [Using TensorFlow’s Dataset API](https://github.com/rasbt/deep-learning-book/blob/master/code/model_zoo/tensorflow_ipynb/dataset-api.ipynb)

## Visual Neural Network

{% embed url="<http://scs.ryerson.ca/~aharley/vis/conv/flat.html>" %}

{% embed url="<https://playground.tensorflow.org>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://stephanosterburg.gitbook.io/scrapbook/career/learn.co/deep-learning-resources.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.