{"id":14977301,"url":"https://github.com/praveen1664/deeplearning-architectures","last_synced_at":"2025-10-28T03:30:51.878Z","repository":{"id":218409703,"uuid":"190993361","full_name":"praveen1664/deeplearning-architectures","owner":"praveen1664","description":"This is one of the deep learning architecture, machine learning, CNN, RNN based on tensorflow, pytorch, tensorboard","archived":false,"fork":false,"pushed_at":"2022-10-13T20:14:20.000Z","size":5478,"stargazers_count":6,"open_issues_count":1,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-01T10:41:36.578Z","etag":null,"topics":["celeba","convolutional-neural-network","deep","deep-neural-networks","ipynb","pytorch","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/praveen1664.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-06-09T10:33:32.000Z","updated_at":"2023-07-29T13:26:26.000Z","dependencies_parsed_at":"2024-01-21T20:16:39.759Z","dependency_job_id":null,"html_url":"https://github.com/praveen1664/deeplearning-architectures","commit_stats":null,"previous_names":["praveen1664/deeplearning-architectures"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praveen1664%2Fdeeplearning-architectures","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praveen1664%2Fdeeplearning-architectures/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praveen1664%2Fdeeplearning-architectures/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/praveen1664%2Fdeeplearning-architectures/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/praveen1664","download_url":"https://codeload.github.com/praveen1664/deeplearning-architectures/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238590593,"owners_count":19497351,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["celeba","convolutional-neural-network","deep","deep-neural-networks","ipynb","pytorch","tensorflow"],"created_at":"2024-09-24T13:55:25.712Z","updated_at":"2025-10-28T03:30:49.060Z","avatar_url":"https://github.com/praveen1664.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Python 3.7](https://img.shields.io/badge/Python-3.7-blue.svg)\n\n# Deep Learning Models\n\nA collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.\n\n## Traditional Machine Learning\n\n- Perceptron [[TensorFlow 1](tensorflow1_ipynb/basic-ml/perceptron.ipynb)] [[PyTorch](pytorch_ipynb/basic-ml/perceptron.ipynb)]\n- Logistic Regression [[TensorFlow 1](tensorflow1_ipynb/basic-ml/logistic-regression.ipynb)] [[PyTorch](pytorch_ipynb/basic-ml/logistic-regression.ipynb)]\n- Softmax Regression (Multinomial Logistic Regression) [[TensorFlow 1](tensorflow1_ipynb/basic-ml/softmax-regression.ipynb)] [[PyTorch](pytorch_ipynb/basic-ml/softmax-regression.ipynb)]\n\n## Multilayer Perceptrons\n\n- Multilayer Perceptron [[TensorFlow 1](tensorflow1_ipynb/mlp/mlp-basic.ipynb)] [[PyTorch](pytorch_ipynb/mlp/mlp-basic.ipynb)]\n- Multilayer Perceptron with Dropout [[TensorFlow 1](tensorflow1_ipynb/mlp/mlp-dropout.ipynb)] [[PyTorch](pytorch_ipynb/mlp/mlp-dropout.ipynb)]\n- Multilayer Perceptron with Batch Normalization [[TensorFlow 1](tensorflow1_ipynb/mlp/mlp-batchnorm.ipynb)] [[PyTorch](pytorch_ipynb/mlp/mlp-batchnorm.ipynb)]\n- Multilayer Perceptron with Backpropagation from Scratch [[TensorFlow 1](tensorflow1_ipynb/mlp/mlp-lowlevel.ipynb)] [[PyTorch](pytorch_ipynb/mlp/mlp-fromscratch__sigmoid-mse.ipynb)]\n\n\n## Convolutional Neural Networks\n\n\n#### Basic\n\n- Convolutional Neural Network [[TensorFlow 1](tensorflow1_ipynb/cnn/cnn-basic.ipynb)] [[PyTorch](pytorch_ipynb/cnn/cnn-basic.ipynb)]\n- Convolutional Neural Network with He Initialization  [[PyTorch](pytorch_ipynb/cnn/cnn-he-init.ipynb)]\n\n#### Concepts\n\n- Replacing Fully-Connnected by Equivalent Convolutional Layers [[PyTorch](pytorch_ipynb/cnn/fc-to-conv.ipynb)]\n\n\n#### Fully Convolutional\n\n- Fully Convolutional Neural Network [[PyTorch](pytorch_ipynb/cnn/cnn-allconv.ipynb)]\n\n#### AlexNet\n\n- AlexNet on CIFAR-10 [[PyTorch](pytorch_ipynb/cnn/cnn-alexnet-cifar10.ipynb)]\n\n#### VGG\n\n- Convolutional Neural Network VGG-16 [[TensorFlow 1](tensorflow1_ipynb/cnn/cnn-vgg16.ipynb)] [[PyTorch](pytorch_ipynb/cnn/cnn-vgg16.ipynb)]\n- VGG-16 Gender Classifier Trained on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-vgg16-celeba.ipynb)]\n- Convolutional Neural Network VGG-19 [[PyTorch](pytorch_ipynb/cnn/cnn-vgg19.ipynb)]\n\n#### ResNet\n\n- ResNet and Residual Blocks [[PyTorch](pytorch_ipynb/cnn/resnet-ex-1.ipynb)]\n- ResNet-18 Digit Classifier Trained on MNIST [[PyTorch](pytorch_ipynb/cnn/cnn-resnet18-mnist.ipynb)]\n- ResNet-18 Gender Classifier Trained on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-resnet18-celeba-dataparallel.ipynb)]\n- ResNet-34 Digit Classifier Trained on MNIST [[PyTorch](pytorch_ipynb/cnn/cnn-resnet34-mnist.ipynb)]\n- ResNet-34 Gender Classifier Trained on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-resnet34-celeba-dataparallel.ipynb)]\n- ResNet-50 Digit Classifier Trained on MNIST [[PyTorch](pytorch_ipynb/cnn/cnn-resnet50-mnist.ipynb)]\n- ResNet-50 Gender Classifier Trained on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-resnet50-celeba-dataparallel.ipynb)]\n- ResNet-101 Gender Classifier Trained on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-resnet101-celeba.ipynb)]\n- ResNet-152 Gender Classifier Trained on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-resnet152-celeba.ipynb)]\n\n#### Network in Network\n\n- Network in Network CIFAR-10 Classifier [[PyTorch](pytorch_ipynb/cnn/nin-cifar10.ipynb)] \n\n\n## Metric Learning\n\n- Siamese Network with Multilayer Perceptrons [[TensorFlow 1](tensorflow1_ipynb/metric/siamese-1.ipynb)]\n\n## Autoencoders\n\n#### Fully-connected Autoencoders\n\n- Autoencoder [[TensorFlow 1](tensorflow1_ipynb/autoencoder/ae-basic.ipynb)] [[PyTorch](pytorch_ipynb/autoencoder/ae-basic.ipynb)]\n\n#### Convolutional Autoencoders\n\n- Convolutional Autoencoder with Deconvolutions / Transposed Convolutions[[TensorFlow 1](tensorflow1_ipynb/autoencoder/ae-deconv.ipynb)] [[PyTorch](pytorch_ipynb/autoencoder/ae-deconv.ipynb)]\n- Convolutional Autoencoder with Deconvolutions (without pooling operations) [[PyTorch](pytorch_ipynb/autoencoder/ae-deconv-nopool.ipynb)]\n- Convolutional Autoencoder with Nearest-neighbor Interpolation [[TensorFlow 1](tensorflow1_ipynb/autoencoder/ae-conv-nneighbor.ipynb)] [[PyTorch](pytorch_ipynb/autoencoder/ae-conv-nneighbor.ipynb)]\n- Convolutional Autoencoder with Nearest-neighbor Interpolation -- Trained on CelebA [[PyTorch](pytorch_ipynb/autoencoder/ae-conv-nneighbor-celeba.ipynb)]\n- Convolutional Autoencoder with Nearest-neighbor Interpolation -- Trained on Quickdraw [[PyTorch](pytorch_ipynb/autoencoder/ae-conv-nneighbor-quickdraw-1.ipynb)]\n\n#### Variational Autoencoders\n\n- Variational Autoencoder [[PyTorch](pytorch_ipynb/autoencoder/ae-var.ipynb)]\n- Convolutional Variational Autoencoder [[PyTorch](pytorch_ipynb/autoencoder/ae-conv-var.ipynb)]\n\n#### Conditional Variational Autoencoders\n\n- Conditional Variational Autoencoder (with labels in reconstruction loss) [[PyTorch](pytorch_ipynb/autoencoder/ae-cvae.ipynb)]\n- Conditional Variational Autoencoder (without labels in reconstruction loss) [[PyTorch](pytorch_ipynb/autoencoder/ae-cvae_no-out-concat.ipynb)]\n- Convolutional Conditional Variational Autoencoder (with labels in reconstruction loss) [[PyTorch](pytorch_ipynb/autoencoder/ae-cnn-cvae.ipynb)]\n- Convolutional Conditional Variational Autoencoder (without labels in reconstruction loss) [[PyTorch](pytorch_ipynb/autoencoder/ae-cnn-cvae_no-out-concat.ipynb)]\n\n## Generative Adversarial Networks (GANs)\n\n- Fully Connected GAN on MNIST [[TensorFlow 1](tensorflow1_ipynb/gan/gan.ipynb)] [[PyTorch](pytorch_ipynb/gan/gan.ipynb)]\n- Convolutional GAN on MNIST [[TensorFlow 1](tensorflow1_ipynb/gan/gan-conv.ipynb)] [[PyTorch](pytorch_ipynb/gan/gan-conv.ipynb)]\n- Convolutional GAN on MNIST with Label Smoothing [[PyTorch](pytorch_ipynb/gan/gan-conv-smoothing.ipynb)]\n\n## Recurrent Neural Networks (RNNs)\n\n\n#### Many-to-one: Sentiment Analysis / Classification\n\n- A simple single-layer RNN (IMDB) [[PyTorch](pytorch_ipynb/rnn/rnn_simple_imdb.ipynb)]\n- A simple single-layer RNN with packed sequences to ignore padding characters (IMDB) [[PyTorch](pytorch_ipynb/rnn/rnn_simple_packed_imdb.ipynb)]\n- RNN with LSTM cells (IMDB) [[PyTorch](pytorch_ipynb/rnn/rnn_lstm_packed_imdb.ipynb)]\n- RNN with LSTM cells (IMDB) and pre-trained GloVe word vectors [[PyTorch](pytorch_ipynb/rnn/rnn_lstm_packed_imdb-glove.ipynb)]\n- RNN with LSTM cells and Own Dataset in CSV Format (IMDB) [[PyTorch](pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb)]\n- RNN with GRU cells (IMDB) [[PyTorch](pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb)]\n- Multilayer bi-directional RNN (IMDB) [[PyTorch](pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb)]\n\n#### Many-to-Many / Sequence-to-Sequence\n\n- A simple character RNN to generate new text (Charles Dickens) [[PyTorch](pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb)]\n\n\n\n## Ordinal Regression\n\n- Ordinal Regression CNN -- CORAL w. ResNet34 on AFAD-Lite [[PyTorch](pytorch_ipynb/ordinal/ordinal-cnn-coral-afadlite.ipynb)]\n- Ordinal Regression CNN -- Niu et al. 2016 w. ResNet34 on AFAD-Lite [[PyTorch](pytorch_ipynb/ordinal/ordinal-cnn-niu-afadlite.ipynb)]\n- Ordinal Regression CNN -- Beckham and Pal 2016 w. ResNet34 on AFAD-Lite [[PyTorch](pytorch_ipynb/ordinal/ordinal-cnn-niu-afadlite.ipynb)]\n\n\n\n\n\n\n## Tips and Tricks\n\n- Cyclical Learning Rate [[PyTorch](pytorch_ipynb/tricks/cyclical-learning-rate.ipynb)]\n\n\n\n## PyTorch Workflows and Mechanics\n\n#### Custom Datasets\n\n- Using PyTorch Dataset Loading Utilities for Custom Datasets -- CSV files converted to HDF5 [[PyTorch](pytorch_ipynb/mechanics/custom-data-loader-csv.ipynb)]\n- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Face Images from CelebA [[PyTorch](pytorch_ipynb/mechanics/custom-data-loader-celeba.ipynb)]\n- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Drawings from Quickdraw [[PyTorch](pytorch_ipynb/mechanics/custom-data-loader-quickdraw.ipynb)]\n- Using PyTorch Dataset Loading Utilities for Custom Datasets -- Drawings from the Street View House Number (SVHN) Dataset [[PyTorch](pytorch_ipynb/mechanics/custom-data-loader-svhn.ipynb)]\n\n#### Training and Preprocessing\n\n- Dataloading with Pinned Memory [[PyTorch](pytorch_ipynb/cnn/cnn-resnet34-cifar10-pinmem.ipynb)]\n- Standardizing Images [[PyTorch](pytorch_ipynb/cnn/cnn-standardized.ipynb)]\n- Image Transformation Examples [[PyTorch](pytorch_ipynb/mechanics/torchvision-transform-examples.ipynb)]\n- Char-RNN with Own Text File [[PyTorch](pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb)]\n- Sentiment Classification RNN with Own CSV File [[PyTorch](pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb)]\n\n\n#### Parallel Computing\n\n- Using Multiple GPUs with DataParallel -- VGG-16 Gender Classifier on CelebA [[PyTorch](pytorch_ipynb/cnn/cnn-vgg16-celeba-data-parallel.ipynb)]\n\n#### Other \n\n- Sequential API and hooks  [[PyTorch](pytorch_ipynb/mlp/mlp-sequential.ipynb)]\n- Weight Sharing Within a Layer  [[PyTorch](pytorch_ipynb/mechanics/cnn-weight-sharing.ipynb)]\n- Plotting Live Training Performance in Jupyter Notebooks with just Matplotlib  [[PyTorch](pytorch_ipynb/mlp/plot-jupyter-matplotlib.ipynb)]\n\n#### Autograd\n\n- Getting Gradients of an Intermediate Variable in PyTorch  [[PyTorch](pytorch_ipynb/mechanics/manual-gradients.ipynb)]\n\n\n\n## TensorFlow Workflows and Mechanics\n\n#### Custom Datasets\n\n- Chunking an Image Dataset for Minibatch Training using NumPy NPZ Archives [[TensorFlow 1](tensorflow1_ipynb/mechanics/image-data-chunking-npz.ipynb)]\n- Storing an Image Dataset for Minibatch Training using HDF5 [[TensorFlow 1](tensorflow1_ipynb/mechanics/image-data-chunking-hdf5.ipynb)]\n- Using Input Pipelines to Read Data from TFRecords Files [[TensorFlow 1](tensorflow1_ipynb/mechanics/tfrecords.ipynb)]\n- Using Queue Runners to Feed Images Directly from Disk [[TensorFlow 1](tensorflow1_ipynb/mechanics/file-queues.ipynb)]\n- Using TensorFlow's Dataset API [[TensorFlow 1](tensorflow1_ipynb/mechanics/dataset-api.ipynb)]\n\n#### Training and Preprocessing\n\n- Saving and Loading Trained Models -- from TensorFlow Checkpoint Files and NumPy NPZ Archives [[TensorFlow 1](tensorflow1_ipynb/mechanics/saving-and-reloading-models.ipynb)]\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpraveen1664%2Fdeeplearning-architectures","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpraveen1664%2Fdeeplearning-architectures","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpraveen1664%2Fdeeplearning-architectures/lists"}