Description
SciSharp's philosophy allows a large number of machine learning code written in Python to be quickly migrated to .NET, enabling .NET developers to use cutting edge machine learning models and access a vast number of Tensorflow resources which would not be possible without this project.
In comparison to other projects, like for instance TensorFlowSharp which only provide Tensorflow's lowlevel C++ API and can only run models that were built using Python, Tensorflow.NET also implements Tensorflow's high level API where all the magic happens. This computation graph building layer is still under active development. Once it is completely implemented you can build new Machine Learning models in C# or F#.
TensorFlow.NET alternatives and similar packages
Based on the "Machine Learning and Data Science" category.
Alternatively, view TensorFlow.NET alternatives based on common mentions on social networks and blogs.

ML.NET
ML.NET is an open source and crossplatform machine learning framework for .NET. 
Accord.NET
Machine learning framework combined with audio and image processing libraries (computer vision, computer audition, signal processing and statistics). 
m2cgen
Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies 
AForge.NET
AForge.NET Framework is a C# framework designed for developers and researchers in the fields of Computer Vision and Artificial Intelligence  image processing, neural networks, genetic algorithms, machine learning, robotics, etc. 
Deedle
Easy to use .NET library for data and time series manipulation and for scientific programming 
Accord.NET Extensions
Advanced image processing and computer vision algorithms made as fluent extensions. 
Spreads
Series and Panels for Realtime and Exploratory Analysis of Data Streams 
Catalyst
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pretrained models, outofthe box support for training word and document embeddings, and flexible entity recognition models. 
Synapses
A group of neuralnetwork libraries for functional and mainstream languages 
Infer.NET
UAI 2015. Kernelbased justintime learning for expectation propagation 
SciSharp STACK
A rich machine learning ecosystem for .NET created by porting the most popular Python libraries to C#.
Scout APM: A developer's best friend. Try free for 14days
* Code Quality Rankings and insights are calculated and provided by Lumnify.
They vary from L1 to L5 with "L5" being the highest.
Do you think we are missing an alternative of TensorFlow.NET or a related project?
README
[logo](docs/assets/tf.net.logo.png)
TensorFlow.NET (TF.NET) provides a .NET Standard binding for TensorFlow. It aims to implement the complete Tensorflow API in C# which allows .NET developers to develop, train and deploy Machine Learning models with the crossplatform .NET Standard framework. TensorFlow.NET has builtin Keras highlevel interface and is released as an independent package TensorFlow.Keras.
master branch is based on tensorflow v2.4, v0.3x branch is based on tensorflow v2.3, v0.15tensorflow1.15 is from tensorflow1.15.
[tensors_flowing](docs/assets/tensors_flowing.gif)
Why TensorFlow in C# and F# ?
SciSharp STACK
's mission is to bring popular data science technology into the .NET world and to provide .NET developers with a powerful Machine Learning tool set without reinventing the wheel. Since the APIs are kept as similar as possible you can immediately adapt any existing TensorFlow code in C# or F# with a zero learning curve. Take a look at a comparison picture and see how comfortably a TensorFlow/Python script translates into a C# program with TensorFlow.NET.
[pythn vs csharp](docs/assets/syntaxcomparision.png)
SciSharp's philosophy allows a large number of machine learning code written in Python to be quickly migrated to .NET, enabling .NET developers to use cutting edge machine learning models and access a vast number of TensorFlow resources which would not be possible without this project.
In comparison to other projects, like for instance TensorFlowSharp which only provide TensorFlow's lowlevel C++ API and can only run models that were built using Python, Tensorflow.NET also implements TensorFlow's high level API where all the magic happens. This computation graph building layer is still under active development. Once it is completely implemented you can build new Machine Learning models in C# or F#.
Go through the online docs TensorFlow for .NET before you get started with Machine Learning in .NET.
How to use
TensorFlow  tf native1.14, cuda 10.0  tf native 1.15, cuda 10.0  tf native 2.3, cuda 10.1  tf native 2.4, cuda 11 

tf.net 0.4x, tf.keras 0.5  x  
tf.net 0.3x, tf.keras 0.4  x  
tf.net 0.2x  x  x  
tf.net 0.15  x  x  
tf.net 0.14  x 
Troubleshooting of running example or installation, please refer [here](tensorflowlib/README.md).
There are many examples reside at TensorFlow.NET Examples written in C# and F#.
C# Example
Install TF.NET and TensorFlow binary through NuGet.
### install tensorflow C#/F# binding
PM> InstallPackage TensorFlow.NET
### install keras for tensorflow
PM> InstallPackage TensorFlow.Keras
### Install tensorflow binary
### For CPU version
PM> InstallPackage SciSharp.TensorFlow.Redist
### For GPU version (CUDA and cuDNN are required)
PM> InstallPackage SciSharp.TensorFlow.RedistWindowsGPU
Import TF.NET and Keras API in your project.
using static Tensorflow.Binding;
using static Tensorflow.KerasApi;
using Tensorflow;
using NumSharp;
Linear Regression in Eager
mode:
// Parameters
var training_steps = 1000;
var learning_rate = 0.01f;
var display_step = 100;
// Sample data
var X = np.array(3.3f, 4.4f, 5.5f, 6.71f, 6.93f, 4.168f, 9.779f, 6.182f, 7.59f, 2.167f,
7.042f, 10.791f, 5.313f, 7.997f, 5.654f, 9.27f, 3.1f);
var Y = np.array(1.7f, 2.76f, 2.09f, 3.19f, 1.694f, 1.573f, 3.366f, 2.596f, 2.53f, 1.221f,
2.827f, 3.465f, 1.65f, 2.904f, 2.42f, 2.94f, 1.3f);
var n_samples = X.shape[0];
// We can set a fixed init value in order to demo
var W = tf.Variable(0.06f, name: "weight");
var b = tf.Variable(0.73f, name: "bias");
var optimizer = keras.optimizers.SGD(learning_rate);
// Run training for the given number of steps.
foreach (var step in range(1, training_steps + 1))
{
// Run the optimization to update W and b values.
// Wrap computation inside a GradientTape for automatic differentiation.
using var g = tf.GradientTape();
// Linear regression (Wx + b).
var pred = W * X + b;
// Mean square error.
var loss = tf.reduce_sum(tf.pow(pred  Y, 2)) / (2 * n_samples);
// should stop recording
// Compute gradients.
var gradients = g.gradient(loss, (W, b));
// Update W and b following gradients.
optimizer.apply_gradients(zip(gradients, (W, b)));
if (step % display_step == 0)
{
pred = W * X + b;
loss = tf.reduce_sum(tf.pow(pred  Y, 2)) / (2 * n_samples);
print($"step: {step}, loss: {loss.numpy()}, W: {W.numpy()}, b: {b.numpy()}");
}
}
Run this example in Jupyter Notebook.
Toy version of ResNet
in Keras
functional API:
var layers = new LayersApi();
// input layer
var inputs = keras.Input(shape: (32, 32, 3), name: "img");
// convolutional layer
var x = layers.Conv2D(32, 3, activation: "relu").Apply(inputs);
x = layers.Conv2D(64, 3, activation: "relu").Apply(x);
var block_1_output = layers.MaxPooling2D(3).Apply(x);
x = layers.Conv2D(64, 3, activation: "relu", padding: "same").Apply(block_1_output);
x = layers.Conv2D(64, 3, activation: "relu", padding: "same").Apply(x);
var block_2_output = layers.Add().Apply(new Tensors(x, block_1_output));
x = layers.Conv2D(64, 3, activation: "relu", padding: "same").Apply(block_2_output);
x = layers.Conv2D(64, 3, activation: "relu", padding: "same").Apply(x);
var block_3_output = layers.Add().Apply(new Tensors(x, block_2_output));
x = layers.Conv2D(64, 3, activation: "relu").Apply(block_3_output);
x = layers.GlobalAveragePooling2D().Apply(x);
x = layers.Dense(256, activation: "relu").Apply(x);
x = layers.Dropout(0.5f).Apply(x);
// output layer
var outputs = layers.Dense(10).Apply(x);
// build keras model
var model = keras.Model(inputs, outputs, name: "toy_resnet");
model.summary();
// compile keras model in tensorflow static graph
model.compile(optimizer: keras.optimizers.RMSprop(1e3f),
loss: keras.losses.CategoricalCrossentropy(from_logits: true),
metrics: new[] { "acc" });
// prepare dataset
var ((x_train, y_train), (x_test, y_test)) = keras.datasets.cifar10.load_data();
x_train = x_train / 255.0f;
y_train = np_utils.to_categorical(y_train, 10);
// training
model.fit(x_train[new Slice(0, 2000)], y_train[new Slice(0, 2000)],
batch_size: 64,
epochs: 10,
validation_split: 0.2f);
F# Example
Linear Regression in Eager
mode:
#r "nuget: TensorFlow.Net"
#r "nuget: TensorFlow.Keras"
#r "nuget: SciSharp.TensorFlow.Redist"
#r "nuget: NumSharp"
open NumSharp
open Tensorflow
open type Tensorflow.Binding
open type Tensorflow.KerasApi
let tf = New<tensorflow>()
tf.enable_eager_execution()
// Parameters
let training_steps = 1000
let learning_rate = 0.01f
let display_step = 100
// Sample data
let train_X =
np.array(3.3f, 4.4f, 5.5f, 6.71f, 6.93f, 4.168f, 9.779f, 6.182f, 7.59f, 2.167f,
7.042f, 10.791f, 5.313f, 7.997f, 5.654f, 9.27f, 3.1f)
let train_Y =
np.array(1.7f, 2.76f, 2.09f, 3.19f, 1.694f, 1.573f, 3.366f, 2.596f, 2.53f, 1.221f,
2.827f, 3.465f, 1.65f, 2.904f, 2.42f, 2.94f, 1.3f)
let n_samples = train_X.shape.[0]
// We can set a fixed init value in order to demo
let W = tf.Variable(0.06f,name = "weight")
let b = tf.Variable(0.73f, name = "bias")
let optimizer = keras.optimizers.SGD(learning_rate)
// Run training for the given number of steps.
for step = 1 to (training_steps + 1) do
// Run the optimization to update W and b values.
// Wrap computation inside a GradientTape for automatic differentiation.
use g = tf.GradientTape()
// Linear regression (Wx + b).
let pred = W * train_X + b
// Mean square error.
let loss = tf.reduce_sum(tf.pow(pred  train_Y,2)) / (2 * n_samples)
// should stop recording
// compute gradients
let gradients = g.gradient(loss,struct (W,b))
// Update W and b following gradients.
optimizer.apply_gradients(zip(gradients, struct (W,b)))
if (step % display_step) = 0 then
let pred = W * train_X + b
let loss = tf.reduce_sum(tf.pow(predtrain_Y,2)) / (2 * n_samples)
printfn $"step: {step}, loss: {loss.numpy()}, W: {W.numpy()}, b: {b.numpy()}"
Read the book The Definitive Guide to Tensorflow.NET if you want to know more about TensorFlow for .NET under the hood.
Contribute:
Feel like contributing to one of the hottest projects in the Machine Learning field? Want to know how Tensorflow magically creates the computational graph? We appreciate every contribution however small. There are tasks for novices to experts alike, if everyone tackles only a small task the sum of contributions will be huge.
You can:
 Let everyone know about this project
 Port Tensorflow unit tests from Python to C# or F#
 Port missing Tensorflow code from Python to C# or F#
 Port Tensorflow examples to C# or F# and raise issues if you come accross missing parts of the API
 Debug one of the unit tests that is marked as Ignored to get it to work
 Debug one of the not yet working examples and get it to work
How to debug unit tests:
The best way to find out why a unit test is failing is to single step it in C# or F# and its corresponding Python at the same time to see where the flow of execution digresses or where variables exhibit different values. Good Python IDEs like PyCharm let you single step into the tensorflow library code.
Git Knowhow for Contributors
Add SciSharp/TensorFlow.NET as upstream to your local repo ...
git remote add upstream [email protected]:SciSharp/TensorFlow.NET.git
Please make sure you keep your fork up to date by regularly pulling from upstream.
git pull upstream master
Contact
Follow us on Twitter, Facebook, Medium, LinkedIn.
Join our chat on Gitter.
Scan QR code to join Tencent TIM group:
[SciSharp STACK](docs/TIM.jpg)
WeChat Sponsor 微信打赏:
[SciSharp STACK](docs/assets/WeChatCollection.jpg)
TensorFlow.NET is a part of SciSharp STACK