https://github.com/iminakov/tensorflow2servingdotnet5client

Implement Tensor Flow 2.0 Serving C# client example with gRPC and Rest. MNIST prediction example and web paint ASP.NET Core 5.0 and ReactJS/Redux application.
https://github.com/iminakov/tensorflow2servingdotnet5client

aspnetcore grpc mnist netcore5 reactredux tensorflow-serving

Last synced: 3 months ago
JSON representation

Implement Tensor Flow 2.0 Serving C# client example with gRPC and Rest. MNIST prediction example and web paint ASP.NET Core 5.0 and ReactJS/Redux application.

• Host: GitHub
• URL: https://github.com/iminakov/tensorflow2servingdotnet5client
• Owner: iminakov
• License: mit
• Created: 2020-12-14T21:09:52.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2020-12-20T17:27:36.000Z (about 4 years ago)
• Last Synced: 2023-02-26T15:45:22.063Z (almost 2 years ago)
• Topics: aspnetcore, grpc, mnist, netcore5, reactredux, tensorflow-serving
• Language: C#
• Homepage:
• Size: 82.8 MB
• Stars: 4
• Watchers: 2
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Tensorflow 2.0 serving .Net Core 5 React/Redux client (GRPC/Rest)

Tensor Flow 2.0 Serving C# client example with gRPC and Rest. There are MNIST CNN prediction model example and ASP.NET Core 5.0 client application with ReactJS/Redux/Typescript front end.

## Repository contains the following content:

- [learning](src/TrainingModel) - python scripts with MNIST CNN model preparing using Keras and Tensorflow 2.0.

- [ClientBaseLib](src/DotnetClient/TensorFlowServingClient) - base library with TF Serving gRPC generated classes and utils classes to create Tensors on C# .NET Core 5 . (Code compatible with TF 1.0)

- [ASP.NET Core 5.0/ ReactJS/Redux Client](src/DotnetClient/TensorFlowServingCSharpClientNet5) - SPA application gRPC/Rest clients for MNIST prediction TensorFlow 2.0 Serving 

## Environment requirements for running example:

- Docker 

- Windows 10

- MSVS 2019 

- VS Code

## How to run example

- Run command promt in root directory in repository

```sh

cd src

```

- Init TensorFlowServing docker image with code (Required only first time)

```sh

init_tensorflow_serving_in_docker.bat

```

- Run trained model in TensorFlowServing docker container

```sh

start run_all_models_serving_in_docker.bat

```

- Build and Run .Net Client Application

```sh

start run_client.bat

```

- Navigate to [http://localhost:5000/](http://localhost:5000/) and test prediction app

## Available examples

### Number prediction example - MNIST, based on simple CNN

![.NET Core 5.0 TensorFlow 2.0 Client](https://user-images.githubusercontent.com/2061634/102206464-ba58ac00-3edd-11eb-8c57-6095091dec12.png)

### Cats and Dogs classification example, based on TensorFlow tutorials and MobileNetV2

![CatsAndDogsPredictionClient](https://user-images.githubusercontent.com/2061634/102719799-41a08800-4301-11eb-8105-06e53c1c675d.png)