Commit 39f05f0e authored by A. Unique TensorFlower's avatar A. Unique TensorFlower
Browse files

Internal change

PiperOrigin-RevId: 303831690
parent b03da6ec
# Legacy Models Collection ![Status](https://img.shields.io/badge/No%20Maintenance%20Intended-%E2%9C%95-red.svg)
The R1 folder contains legacy model implmentation and models that will not # Legacy Models
update to TensorFlow 2.x. They do not have solid performance tracking.
**Note: models will be removed from the master branch by 2020/06.** The **r1** folder contains legacy model implementations developed
using TensorFlow 1.x.
After removal, you can still access to these legacy models in the previous **Note: We will remove this r1 folder from the master branch in June, 2020.**
released tags, e.g. [v2.1.0](https://github.com/tensorflow/models/releases/tag/v2.1.0).
After removal, you will still be able to access legacy models
in the previous releases.
(e.g., [v2.1.0](https://github.com/tensorflow/models/releases/tag/v2.1.0))
## Legacy model implmentation | Model | Description | Reference |
| ----- | ----------- | --------- |
Transformer and MNIST implementation uses pure TF 1.x TF-Estimator. | [Gradient Boosted Trees](boosted_trees) | A gradient boosted trees model to classify higgs boson process from HIGGS dataset | [Link](https://en.wikipedia.org/wiki/Gradient_boosting) |
Users should follow the corresponding TF 2.x implmentation inside the | [MNIST](mnist) | A basic model to classify digits from the MNIST dataset | [Link](http://yann.lecun.com/exdb/mnist/) |
official model garden. | [ResNet](resnet) | A deep residual network for image recognition | [arXiv:1512.03385](https://arxiv.org/abs/1512.03385) |
| [Transformer](transformer) | A transformer model to translate the WMT English to German dataset | [arXiv:1706.03762](https://arxiv.org/abs/1706.03762) |
## Models that will not update to TensorFlow 2.x | [Wide & Deep Learning](wide_deep) | A model that combines a wide linear model and deep neural network for recommender systems | [arXiv:1606.07792](https://arxiv.org/abs/1606.07792) |
* [boosted_trees](boosted_trees): A Gradient Boosted Trees model to
classify higgs boson process from HIGGS Data Set.
* [wide_deep](wide_deep): A model that combines a wide model and deep
network to classify census income data.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment