fanyuchang/DeepLearning-Tutorials

This repository is about tutorials of Deep Learning in Keras and Tensorflow.

Deep Learning

Some repositories about Deep Learning:

Frameworks

• tensorflow - An Open Source Machine Learning Framework for Everyone.
• Keras - Keras: Deep Learning for humans.
• tensorforce - Tensorforce: a TensorFlow library for applied reinforcement learning.

Learning Source

• MIT Deep Learning Book - MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville.
• Deep-Learning-Papers - A list of deep learning papers and notes on them.
• Computational-Physics-and-Machine-Learning-Reading-List - A list of papers relating Computational Physics and Machine Learning.

Tutorials

• Keras-Tutorials - Keras-Tutorials.
• Keras-Tutorials - Simple tutorials using Keras Framework.
• Memory-Efficient-Autoencoder - A repo looking at autoencoders that can be applied to extremely large 2D and 3D tensors.
• Convolutional-LSTM-in-Tensorflow - An implementation of convolutional lstms in tensorflow. The code is written in the same style as the basiclstmcell function in tensorflow.
• Variational-autoencoder-tricks-and-tips - just a few trouble shooting tips I have found for training variational autoencoders. All code in tensorflow.
• All-Convnet-Autoencoder-Example - Just a simple use example of the conv2d_transpose function in TensorFlow. Its run on MNIST.

Flow Control:

• Cylinder2DFlowControlWithRL - Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control, Journal of Fluid Mechanics, 2019.
• Cylinder2DFlowControlDRLParallel - Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach", Rabault and Kuhnle, Physics of Fluids, 2019.
• Deep Flow Control - Source code for "Deep Dynamical Modeling and Control of Unsteady Fluid Flows" from NIPS 2018.
• CS230_FinalReport - Final report for CS230 Project "Deep Reinforcement Learning for Unsteady Flow Control".

Reduced Order Modeling

• LSTM_ROM_Arxiv - A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks.
• ROM_code - Construction of reduced-order models for fluid flows using deep feedforward neural networks. Journal of Fluid Mechanics, 2019.
• MD-CNN-AE - Nonlinear mode decomposition with convolutional neural networks for fluid dynamics, Journal of Fluid Mechanics, 2020.
• Reconstruction-of-Flows - Reconstruction of Flows using Convolutional neural networks, 2019.
• LabelFree-DNN-Surrogate - Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data, 2020.
• Super-resolution-reconstruction - Super-resolution reconstruction of turbulent flows with machine learning, JFM, 2019

Physics Inform

• DeepXDE - Deep learning library for solving differential equations.

Computational Fluid Dynamics (Continuum Methods)

• Cylinder - Computational Fluid-Dynamics Machine Learning Examples.
• tf-cfd - Computational fluid dynamics with tensorflow.
• Steady-State-Flow-With-Neural-Nets - A Tensorflow re-implementation of the paper Convolutional Neural Networks for Steady Flow Approximation.
• RKNN - Deep learning of dynamics and signal noise decomposition with time-stepping constraints.
• Flow-Sculpter - Neural Networks learning to create objects with desired flow properties.

Lattice Boltzmann Method

• Phy-Net - Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks.
• Lattice-Boltzmann-fluid-flow-in-Tensorflow - A Lattice Boltzmann fluid flow simulation written in Tensorflow.
• latnet - Neural Network Based Lattice Boltzmann solver.

Turbulence Modeling

• turbulence_model_neural_network_with_data_processing - turbulence model neural network with data processing, include data cleaning and data post-processing.
• machine-learning-turbulence - Machine Learning in Turbulence Modeling.
• tbnn - Reynolds averaged turbulence modelling using deep neural networks with embedded invariance, Journal of Fluid Mechanics, 2016.
• DNNLESMODEL - This repository contains the python code, weight and bias matrices for the INU model.
• Deep-Flow-Prediction - Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows

Aerodynamics

• CNN-for-Airfoil - CNN for airfoil lift-to-drag-ratio prediction.

Aerospace

• Turbulence - This repository contains code to make a neural network that determines if an aircraft is flying through very turbulent, somewhat turbulent, or calm weather based on accelerometer readings. This also includes datasets and unlabeled data that requires processing to be used as datasets. The neural networks are written in Python, using Keras with Te …