mirrors / rasbt--deeplearning-models

项目文件夹

rasbt--deeplearning-models
文件
lenet5
T
rasbt 42508702ca pytorch plot_decision_region wrapper
2019-12-29 13:00:33 +00:00

345 行
32 KiB
Markdown
原始文件 永久链接 Blame 文件历史

![Python 3.7](https://img.shields.io/badge/Python-3.7-blue.svg)
# Deep Learning Models
A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.
## Traditional Machine Learning
- Perceptron
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/basic-ml/perceptron.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/basic-ml/perceptron.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/basic-ml/perceptron.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/perceptron.ipynb)]
- Logistic Regression
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/basic-ml/logistic-regression.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/basic-ml/logistic-regression.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/basic-ml/logistic-regression.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/logistic-regression.ipynb)]
- Softmax Regression (Multinomial Logistic Regression)
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/basic-ml/softmax-regression.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/basic-ml/softmax-regression.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/basic-ml/softmax-regression.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/softmax-regression.ipynb)]
- Softmax Regression with MLxtend's plot_decision_regions on Iris
   [PyTorch: [GitHub](pytorch_ipynb/basic-ml/softmax-regression-mlxtend-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/softmax-regression-mlxtend-1.ipynb)]
## Multilayer Perceptrons
- Multilayer Perceptron
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mlp/mlp-basic.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-basic.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/mlp/mlp-basic.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-basic.ipynb)]
- Multilayer Perceptron with Dropout
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mlp/mlp-dropout.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-dropout.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/mlp/mlp-dropout.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-dropout.ipynb)]
- Multilayer Perceptron with Batch Normalization
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mlp/mlp-batchnorm.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-batchnorm.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/mlp/mlp-batchnorm.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-batchnorm.ipynb)]
- Multilayer Perceptron with Backpropagation from Scratch
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mlp/mlp-lowlevel.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-lowlevel.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/mlp/mlp-fromscratch__sigmoid-mse.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-fromscratch__sigmoid-mse.ipynb)]
## Convolutional Neural Networks
#### Basic
- Convolutional Neural Network
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/cnn/cnn-basic.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/cnn/cnn-basic.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-basic.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-basic.ipynb)]
- Convolutional Neural Network with He Initialization
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-he-init.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-he-init.ipynb)]
#### Concepts
- Replacing Fully-Connnected by Equivalent Convolutional Layers
   [PyTorch: [GitHub](pytorch_ipynb/cnn/fc-to-conv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/fc-to-conv.ipynb)]
#### Fully Convolutional
- Fully Convolutional Neural Network
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-allconv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-allconv.ipynb)]
#### LeNet
- LeNet-5 on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-lenet5-mnist.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-lenet5-mnist.ipynb)]
- LeNet-5 on CIFAR-10
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-lenet5-cifar10.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-lenet5-cifar10.ipynb)]
- LeNet-5 on QuickDraw
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-lenet5-quickdraw.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-lenet5-quickdraw.ipynb)]
#### AlexNet
- AlexNet on CIFAR-10
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-alexnet-cifar10.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-alexnet-cifar10.ipynb)]
#### VGG
- Convolutional Neural Network VGG-16
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/cnn/cnn-vgg16.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/cnn/cnn-vgg16.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-vgg16.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg16.ipynb)]
- VGG-16 Gender Classifier Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-vgg16-celeba.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg16-celeba.ipynb)]
- Convolutional Neural Network VGG-19
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-vgg19.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg19.ipynb)]
#### DenseNet
- DenseNet-121 Digit Classifier Trained on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-densenet121-mnist.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-densenet121-mnist.ipynb)]
- DenseNet-121 Image Classifier Trained on CIFAR-10
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-densenet121-cifar10.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-densenet121-cifar10.ipynb)]
#### ResNet
- ResNet and Residual Blocks
   [PyTorch: [GitHub](pytorch_ipynb/cnn/resnet-ex-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/resnet-ex-1.ipynb)]
- ResNet-18 Digit Classifier Trained on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet18-mnist.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet18-mnist.ipynb)]
- ResNet-18 Gender Classifier Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet18-celeba-dataparallel.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet18-celeba-dataparallel.ipynb)]
- ResNet-34 Digit Classifier Trained on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet34-mnist.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-mnist.ipynb)]
- ResNet-34 Object Classifier Trained on QuickDraw
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet34-quickdraw.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-quickdraw.ipynb)]
- ResNet-34 Gender Classifier Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet34-celeba-dataparallel.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-celeba-dataparallel.ipynb)]
- ResNet-50 Digit Classifier Trained on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet50-mnist.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet50-mnist.ipynb)]
- ResNet-50 Gender Classifier Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet50-celeba-dataparallel.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet50-celeba-dataparallel.ipynb)]
- ResNet-101 Gender Classifier Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet101-celeba.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet101-celeba.ipynb)]
- ResNet-101 Trained on CIFAR-10
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet101-cifar10.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet101-cifar10.ipynb)]
- ResNet-152 Gender Classifier Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet152-celeba.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet152-celeba.ipynb)]
#### Network in Network
- Network in Network CIFAR-10 Classifier
   [PyTorch: [GitHub](pytorch_ipynb/cnn/nin-cifar10.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/nin-cifar10.ipynb)]
## Normalization Layers
- BatchNorm before and after Activation for Network-in-Network CIFAR-10 Classifier
   [PyTorch: [GitHub](pytorch_ipynb/cnn/nin-cifar10_batchnorm.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/nin-cifar10_batchnorm.ipynb)]
- Filter Response Normalization for Network-in-Network CIFAR-10 Classifier
   [PyTorch: [GitHub](pytorch_ipynb/cnn/nin-cifar10_filter-response-norm.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/nin-cifar10_filter-response-norm.ipynb)]
## Metric Learning
- Siamese Network with Multilayer Perceptrons
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/metric/siamese-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/metric/siamese-1.ipynb)]
## Autoencoders
#### Fully-connected Autoencoders
- Autoencoder (MNIST)
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/autoencoder/ae-basic.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/ae-basic.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-basic.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-basic.ipynb)]
- Autoencoder (MNIST) + Scikit-Learn Random Forest Classifier
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/autoencoder/ae-basic-with-rf.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/ae-basic.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-basic-with-rf.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-basic.ipynb)]
#### Convolutional Autoencoders
- Convolutional Autoencoder with Deconvolutions / Transposed Convolutions
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/autoencoder/ae-deconv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/ae-deconv.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-deconv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-deconv.ipynb)]
- Convolutional Autoencoder with Deconvolutions and Continuous Jaccard Distance
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-deconv-jaccard.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-deconv-jaccard.ipynb)]
- Convolutional Autoencoder with Deconvolutions (without pooling operations)
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-deconv-nopool.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-deconv-nopool.ipynb)]
- Convolutional Autoencoder with Nearest-neighbor Interpolation
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/autoencoder/ae-conv-nneighbor.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/ae-conv-nneighbor.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-conv-nneighbor.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-nneighbor.ipynb)]
- Convolutional Autoencoder with Nearest-neighbor Interpolation -- Trained on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-conv-nneighbor-celeba.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-nneighbor-celeba.ipynb)]
- Convolutional Autoencoder with Nearest-neighbor Interpolation -- Trained on Quickdraw
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-conv-nneighbor-quickdraw-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-nneighbor-quickdraw-1.ipynb)]
#### Variational Autoencoders
- Variational Autoencoder
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-var.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-var.ipynb)]
- Convolutional Variational Autoencoder
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-conv-var.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-var.ipynb)]
#### Conditional Variational Autoencoders
- Conditional Variational Autoencoder (with labels in reconstruction loss)
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-cvae.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cvae.ipynb)]
- Conditional Variational Autoencoder (without labels in reconstruction loss)
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-cvae_no-out-concat.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cvae_no-out-concat.ipynb)]
- Convolutional Conditional Variational Autoencoder (with labels in reconstruction loss)
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-cnn-cvae.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cnn-cvae.ipynb)]
- Convolutional Conditional Variational Autoencoder (without labels in reconstruction loss)
   [PyTorch: [GitHub](pytorch_ipynb/autoencoder/ae-cnn-cvae_no-out-concat.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cnn-cvae_no-out-concat.ipynb)]
## Generative Adversarial Networks (GANs)
- Fully Connected GAN on MNIST
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/gan/gan.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/gan/gan.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/gan/gan.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/gan.ipynb)]
- Fully Connected Wasserstein GAN on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/gan/wgan-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/wgan-1.ipynb)]
- Convolutional GAN on MNIST
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/gan/gan-conv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/gan/gan-conv.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/gan/gan-conv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/gan-conv.ipynb)]
- Convolutional GAN on MNIST with Label Smoothing
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/gan/gan-conv-smoothing.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/gan/gan-conv-smoothing.ipynb)]
   [PyTorch: [GitHub](pytorch_ipynb/gan/gan-conv-smoothing.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/gan-conv-smoothing.ipynb)]
- Convolutional Wasserstein GAN on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/gan/dc-wgan-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/dc-wgan-1.ipynb)]
## Graph Neural Networks (GNNs)
- Most Basic Graph Neural Network with Gaussian Filter on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/gnn/gnn-basic-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gnn/gnn-basic-1.ipynb)]
- Basic Graph Neural Network with Edge Prediction on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/gnn/gnn-basic-edge-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gnn/gnn-basic-edge-1.ipynb)]
- Basic Graph Neural Network with Spectral Graph Convolution on MNIST
   [PyTorch: [GitHub](pytorch_ipynb/gnn/gnn-basic-graph-spectral-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gnn/gnn-basic-graph-spectral-1.ipynb)]
## Recurrent Neural Networks (RNNs)
#### Many-to-one: Sentiment Analysis / Classification
- A simple single-layer RNN (IMDB)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_simple_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_simple_imdb.ipynb)]
- A simple single-layer RNN with packed sequences to ignore padding characters (IMDB)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_simple_packed_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_simple_packed_imdb.ipynb)]
- RNN with LSTM cells (IMDB)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_lstm_packed_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_imdb.ipynb)]
- RNN with LSTM cells (IMDB) and pre-trained GloVe word vectors
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_lstm_packed_imdb-glove.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_imdb-glove.ipynb)]
- RNN with LSTM cells and Own Dataset in CSV Format (IMDB)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb)]
- RNN with GRU cells (IMDB)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb)]
- Multilayer bi-directional RNN (IMDB)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb)]
- Bidirectional Multi-layer RNN with LSTM with Own Dataset in CSV Format (AG News)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_bi_multilayer_lstm_own_csv_agnews.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_bi_multilayer_lstm_own_csv_agnews.ipynb)]
- Bidirectional Multi-layer RNN with LSTM with Own Dataset in CSV Format (Yelp Review Polarity)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_bi_multilayer_lstm_own_csv_yelp-polarity.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_bi_multilayer_lstm_own_csv_yelp-polarity.ipynb)]
- Bidirectional Multi-layer RNN with LSTM with Own Dataset in CSV Format (Amazon Review Polarity)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_bi_multilayer_lstm_own_csv_amazon-polarity.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_bi_multilayer_lstm_own_csv_amazon-polarity.ipynb)]
#### Many-to-Many / Sequence-to-Sequence
- A simple character RNN to generate new text (Charles Dickens)
   [PyTorch: [GitHub](pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb)]
## Ordinal Regression
- Ordinal Regression CNN -- CORAL w. ResNet34 on AFAD-Lite
   [PyTorch: [GitHub](pytorch_ipynb/ordinal/ordinal-cnn-coral-afadlite.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/ordinal/ordinal-cnn-coral-afadlite.ipynb)]
- Ordinal Regression CNN -- Niu et al. 2016 w. ResNet34 on AFAD-Lite
   [PyTorch: [GitHub](pytorch_ipynb/ordinal/ordinal-cnn-niu-afadlite.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/ordinal/ordinal-cnn-niu-afadlite.ipynb)]
- Ordinal Regression CNN -- Beckham and Pal 2016 w. ResNet34 on AFAD-Lite
   [PyTorch: [GitHub](pytorch_ipynb/ordinal/ordinal-cnn-beckham2016-afadlite.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/ordinal/ordinal-cnn-beckham2016-afadlite.ipynb)]
## Tips and Tricks
- Cyclical Learning Rate
   [PyTorch: [GitHub](pytorch_ipynb/tricks/cyclical-learning-rate.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/tricks/cyclical-learning-rate.ipynb)]
- Annealing with Increasing the Batch Size (w. CIFAR-10 & AlexNet)
   [PyTorch: [GitHub](pytorch_ipynb/tricks/cnn-alexnet-cifar10-batchincrease.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/tricks/cnn-alexnet-cifar10-batchincrease.ipynb)]
- Gradient Clipping (w. MLP on MNIST)
   [PyTorch: [GitHub](pytorch_ipynb/tricks/gradclipping_mlp.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/tricks/gradclipping_mlp.ipynb)]
## Transfer Learning
- Transfer Learning Example (VGG16 pre-trained on ImageNet for Cifar-10)
   [PyTorch: [GitHub](pytorch_ipynb/transfer/transferlearning-vgg16-cifar10-1.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/transfer/transferlearning-vgg16-cifar10-1.ipynb)]
## PyTorch Workflows and Mechanics
#### Custom Datasets
- Custom Data Loader Example for PNG Files
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-dataloader-png/custom-dataloader-example.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-dataloader-png/custom-dataloader-example.ipynb)]
- Using PyTorch Dataset Loading Utilities for Custom Datasets -- CSV files converted to HDF5
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-data-loader-csv.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-csv.ipynb)]
- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Face Images from CelebA
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-data-loader-celeba.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-celeba.ipynb)]
- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Drawings from Quickdraw
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-data-loader-quickdraw.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-quickdraw.ipynb)]
- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Drawings from the Street View House Number (SVHN) Dataset
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-data-loader-svhn.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-svhn.ipynb)]
- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Asian Face Dataset (AFAD)
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-data-loader-afad.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-afad.ipynb)]
- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Dating Historical Color Images
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/custom-data-loader_dating-historical-color-images.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader_dating-historical-color-images.ipynb)]
#### Training and Preprocessing
- Generating Validation Set Splits
[PyTorch]: [GitHub](pytorch_ipynb/mechanics/validation-splits.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/validation-splits.ipynb)]
- Dataloading with Pinned Memory
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-resnet34-cifar10-pinmem.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-cifar10-pinmem.ipynb)]
- Standardizing Images
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-standardized.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-standardized.ipynb)]
- Image Transformation Examples
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/torchvision-transform-examples.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/torchvision-transform-examples.ipynb)]
- Char-RNN with Own Text File
   [PyTorch: [GitHub](pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb)]
- Sentiment Classification RNN with Own CSV File
   [PyTorch: [GitHub](pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb)]
#### Parallel Computing
- Using Multiple GPUs with DataParallel -- VGG-16 Gender Classifier on CelebA
   [PyTorch: [GitHub](pytorch_ipynb/cnn/cnn-vgg16-celeba-data-parallel.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg16-celeba-data-parallel.ipynb)]
#### Other
- Sequential API and hooks
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/mlp-sequential.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/mlp-sequential.ipynb)]
- Weight Sharing Within a Layer
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/cnn-weight-sharing.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/cnn-weight-sharing.ipynb)]
- Plotting Live Training Performance in Jupyter Notebooks with just Matplotlib
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/plot-jupyter-matplotlib.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/plot-jupyter-matplotlib.ipynb)]
#### Autograd
- Getting Gradients of an Intermediate Variable in PyTorch
   [PyTorch: [GitHub](pytorch_ipynb/mechanics/manual-gradients.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/manual-gradients.ipynb)]
## TensorFlow Workflows and Mechanics
#### Custom Datasets
- Chunking an Image Dataset for Minibatch Training using NumPy NPZ Archives
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mechanics/image-data-chunking-npz.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/image-data-chunking-npz.ipynb)]
- Storing an Image Dataset for Minibatch Training using HDF5
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mechanics/image-data-chunking-hdf5.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/image-data-chunking-hdf5.ipynb)]
- Using Input Pipelines to Read Data from TFRecords Files
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mechanics/tfrecords.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/tfrecords.ipynb)]
- Using Queue Runners to Feed Images Directly from Disk
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mechanics/file-queues.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/file-queues.ipynb)]
- Using TensorFlow's Dataset API
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mechanics/dataset-api.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/dataset-api.ipynb)]
#### Training and Preprocessing
- Saving and Loading Trained Models -- from TensorFlow Checkpoint Files and NumPy NPZ Archives
   [TensorFlow 1: [GitHub](tensorflow1_ipynb/mechanics/saving-and-reloading-models.ipynb) | [Nbviewer](https://nbviewer.jupyter.org/github/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/saving-and-reloading-models.ipynb)]
在新工单中引用 查看 Git Blame 复制永久链接