17 best open source tensorflow models projects.

AndroidTensorFlowMachineLearningExample - Android TensorFlow MachineLearning Example (Building TensorFlow for Android)

Java

Android TensorFlow MachineLearning Example (Building TensorFlow for Android)

tensorflow tensorflow-tutorials tensorflow-android machine-learning machine-learning-android tensorflow-models tensorflow-examples deep-learning deep-neural-networks deeplearning deep-learning-tutorial

Awesome-CoreML-Models - Largest list of models for Core ML (for iOS 11+)

HTML

We've put up the largest collection of machine learning models in Core ML format, to help iOS, macOS, tvOS, and watchOS developers experiment with machine learning techniques. We've created a site with better visualization of the models CoreML.Store, and are working on more advance features. If you've converted a Core ML model, feel free to submit an issue.

coreml coreml-model apple machine-learning curated-list coreml-framework coreml-models coremltools awesome-list models model download awesome core-ml ml caffe caffemodel tensorflow-models ios ios11

AndroidTensorFlowMNISTExample - Android TensorFlow MachineLearning MNIST Example (Building Model with TensorFlow for Android)

Java

All pull requests are welcome, make sure to follow the contribution guidelines when you submit pull request.

tensorflow tensorflow-tutorials mnist-classification mnist machine-learning android tensorflow-models machine-learning-android tensorflow-android tensorflow-model mnist-model deep-learning deep-neural-networks deeplearning deep-learning-tutorial

simple_tensorflow_serving - Generic and easy-to-use serving service for machine learning models

Javascript

Simple TensorFlow Serving is the generic and easy-to-use serving service for machine learning models. Read more in https://stfs.readthedocs.io. Install the server with pip.

tensorflow-models savedmodel tensorflow serving client http machine-learning deep-learning

tensorlayer-tricks - How to use TensorLayer

While research in Deep Learning continues to improve the world, we use a bunch of tricks to implement algorithms with TensorLayer day to day. Here are a summary of the tricks to use TensorLayer. If you find a trick that is particularly useful in practice, please open a Pull Request to add it to the document. If we find it to be reasonable and verified, we will merge it in.

tensorlayer tensorflow deep-learning machine-learning data-science neural-network reinforcement-learning neural-networks tensorflow-tutorials tensorflow-models computer-vision tensorflow-framework tensorflow-library tflearn keras tensorboard nlp natural-language-processing lasagne tensorflow-experiments

kemono_puyo - :cat: Take kemono pictures and lines up 3, then tanoshii

Javascript

This is a toy application that made at the hackathon. It is inspired by following two concepts. At first I tried to implement the feature to control the falling objects but to see the animal faces is so fun and cute. Because of this, I dropped its implementation.

tensorflow tensorflow-models object-detection kemono-friends

tensorflow-kubernetes-art-classification - Train a TensorFlow model on Kubernetes to recognize art culture based on the collection from the Metropolitan Museum of Art

Python

Read this in other languages: 中国. In this Code Pattern, we will use Deep Learning to train an image classification model. The data comes from the art collection at the New York Metropolitan Museum of Art and the metadata from Google BigQuery. We will use the Inception model implemented in TensorFlow and we will run the training on a Kubernetes cluster. We will save the trained model and load it later to perform inference. To use the model, we provide as input a picture of a painting and the model will return the likely culture, for instance "Italian, Florence" art. The user can choose other attributes to classify the art collection, for instance author, time period, etc. Depending on the compute resources available, the user can choose the number of images to train, the number of classes to use, etc. In this Code Pattern, we will select a small set of images and a small number of classes to allow the training to complete within a reasonable amount of time. With a large dataset, the training may take days or weeks.

tensorflow-models image-classification deep-learning ibm-bluemix kubernetes-cluster ibmcode

steppy-toolkit - Curated set of transformers that make your work with steppy faster and more effective :telescope:

Python

Set of tools to make your work with Steppy faster and more effective. Steppy is a lightweight, open-source, Python library for fast and reproducible experimentation.

pipeline data-science machine-learning deep-learning steps nlp reproducible-research reproducibility steppy steppy-toolkit python3 keras tensorflow tensorflow-models keras-models pytorch pytorch-models open-source pipeline-framework

TFaaS - TensorFlow as a Service, a general purpose framework to serve TF models.

Javascript

A general purpose framework (written in Go) to serve TensorFlow models. It provides reach and flexible set of APIs to efficiently access your favorite TF models via HTTP interface. The TFaaS supports JSON and ProtoBuffer data-formats. Fore more information please visit curl client page.

tensorflow tf-model inference machine-learning deeplearning tensorflow-models prediction tfaas-server

tf-bridge - Tensor Bridge: OpenAPI spec and REST wrapper around TensorFlow Serving

Python

Tensor Bridge is an OpenAPI Specification as well as a simple Connexion wrapper for TensorFlow Serving. The specification was obtained by compiling an annotated tensor_bridge.proto using grpc-gateway. The result is located in swagger/tensor_bridge.json.

tensorflow-serving tensorflow tensorflow-models machine-learning machine-learning-api

GAN-Project-2018 - GAN in Tensorflow to be run via Linux command line

Python

If you are sure all the libraries in requirements.txt are installed, go to $ python main.py ...

dcgan dcgan-tensorflow dcgan-mnist-tutorial tensorflow tensorflow-models linux-kernel generative-adversarial-network gan generative-adversarial-networks

tensorflow-convolution-models

Jupyter

This repo also contains a notebook that shows the result of the different steps in the convolutional architectures.

tensorflow convolutional-models convolution cnn cnn-model cnn-architecture tensorflow-models

Mango - Question Answering NLP w/ character-level RNN w/ TensorFlow! ℳ🖊 (QRN and EntNet)

Python

The different models will first be challenged with the bAbI dataset from FAIR and the SQuAD dataset from Stanford. EntNet: very soon ...

deep-learning machine-learning qrn entnet tensorflow rnn rnn-tensorflow tensorflow-experiments tensorflow-models

cramer-gan - Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv

Python

Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv.org/pdf/1705.10743.pdf)

tensorflow generative-adversarial-network generative-model generative tensorflow-experiments tensorflow-models wasserstein-gan cramer-gan

fast-weights - Implementation of the paper [Using Fast Weights to Attend to the Recent Past](https://arxiv

Python

This script generates a file called associative-retrieval.pkl, which can be used for training. The following is the accuracy and loss graph for R=20. The experiments are barely tuned.

fast-weights accuracy tensorflow tensorflow-models deep-learning

wgan - Tensorflow Implementation of Wasserstein GAN (and Improved version in wgan_v2)

Python

Tensorflow implementation of Wasserstein GAN.

tensorflow generative generative-adversarial-network generative-model tensorflow-models tensorflow-experiments

tensorflow_template - A simple template for tensorflow project. A high-level version:

Python

A deep learning template for tensorflow, of which the idea is from another project MrGemy95/Tensorflow-Project-Template. All you need to do is finish the following four functions.

tensorflow tensorflow-template tensorflow-models tensorflow-tutorials neural-network