cff-version: 1.2.0
message: "If you use TensorFlow in your research, please cite it using these metadata. Software is available from tensorflow.org."
title: TensorFlow, Large-scale machine learning on heterogeneous systems

* **Machine Learning**: Normalmente exige muita multiplicação de matrizes e vetores. Pense numa grande folha de papel com números e multiplicando todos eles juntos e ao mesmo tempo.

* L'apprentissage automatique (ou **Machine Learning**) : cela nécessite de nombreuses multiplications de matrices et vecteurs. Imaginez une énorme feuille de calcul remplie de nombres que vous multiplierez entre eux tous au même moment.

## Caso de uso

Vamos iniciar com um exemplo de **caso de uso** e então ver como resolvê-lo com isso.

Vamos imaginar que você tem alguns **modelos de _machine learning_** que deseja usar para lidar com as requisições. 🤖

    title: 'Uber: Ludwig v0.2 Adds New Features and Other Improvements to its Deep Learning Toolbox [including a FastAPI server]'
  - author: Maarten Grootendorst
    author_link: https://www.linkedin.com/in/mgrootendorst/
    link: https://towardsdatascience.com/how-to-deploy-a-machine-learning-model-dc51200fe8cf
    title: How to Deploy a Machine Learning Model
  - author: Johannes Gontrum
    author_link: https://twitter.com/gntrm

* **Machine Learning**: normalmente requiere muchas multiplicaciones de "matrices" y "vectores". Imagina en una enorme hoja de cálculo con números y tener que multiplicarlos todos al mismo tiempo.

Some course providers ✨ [**sponsor FastAPI**](../help-fastapi.md#sponsor-the-author){.internal-link target=_blank} ✨, this ensures the continued and healthy **development** of FastAPI and its **ecosystem**.

## Use Case

Let's start with an example **use case** and then see how to solve it with this.

Let's imagine that you have some **machine learning models** that you want to use to handle requests. 🤖

* **Machine Learning**: it normally requires lots of "matrix" and "vector" multiplications. Think of a huge spreadsheet with numbers and multiplying all of them together at the same time.

app = FastAPI()


@app.get("/models/{model_name}")
async def get_model(model_name: ModelName):
    if model_name is ModelName.alexnet:
        return {"model_name": model_name, "message": "Deep Learning FTW!"}

    if model_name.value == "lenet":
        return {"model_name": model_name, "message": "LeCNN all the images"}