<b>Archai</b> accelerates your Neural Architecture Search (NAS) through <b>fast</b>, <b>reproducible</b> and <b>modular</b> research, enabling the generation of efficient deep networks for various applications.
Archai can be installed through various methods, however, it is recommended to utilize a virtual environment such as `conda` or `pyenv` for optimal results.
In this quickstart example, we will apply Archai in Natural Language Processing to find the optimal Pareto-frontier Transformers' configurations according to a set of objectives.
### Creating the Search Space
We start by importing the `TransformerFlexSearchSpace` class which represents the search space for the Transformer architecture:
```python
from archai.discrete_search.search_spaces.nlp.transformer_flex.search_space import TransformerFlexSearchSpace
space = TransformerFlexSearchSpace("gpt2")
```
### Defining Search Objectives
Next, we define the objectives we want to optimize. In this example, we use `NonEmbeddingParamsProxy`, `TransformerFlexOnnxLatency`, and `TransformerFlexOnnxMemory` to define the objectives:
The algorithm will iterate through different network architectures, evaluate their performance based on the defined objectives, and ultimately produce a frontier of Pareto-optimal results.
The [official documentation](https://microsoft.github.io/archai) also provides a series of [notebooks](https://microsoft.github.io/archai/getting_started/notebooks.html).
If you have any questions or feedback about the Archai project or the open problems in Neural Architecture Search, please feel free to contact us using the following information:
Archai has been created and maintained by [Shital Shah](https://shital.com), [Debadeepta Dey](https://debadeepta.com), [Gustavo de Rosa](https://www.microsoft.com/en-us/research/people/gderosa), Caio Mendes, [Piero Kauffmann](https://www.microsoft.com/en-us/research/people/pkauffmann), [Chris Lovett](https://lovettsoftware.com), Allie Del Giorno, Mojan Javaheripi, and [Ofer Dekel](https://www.microsoft.com/en-us/research/people/oferd) at Microsoft Research.
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com.
When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repositories using our CLA.
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.
