* cross origin: cross origin (do not translate to "origem cruzada")
* Cross-Origin Resource Sharing: Cross-Origin Resource Sharing (do not translate to "Compartilhamento de Recursos de Origem Cruzada")
* Deep Learning: Deep Learning (do not translate to "Aprendizado Profundo")
* dependable: dependable
* dependencies: dependências
* deprecated: descontinuado
* docs: documentação
* FastAPI app: aplicação FastAPI

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

* production (meaning production software or environment): продакшн (do not change the ending, for example, translate `in production` as `в продакшн` (not `в продакшене`))
* completion (meaning code auto-completion): автозавершение
* editor (meaning component of IDE): редактор кода
* adopt (meaning start to use): использовать (or `начать использовать`)
* headers (meaning HTTP-headers): HTTP-заголовки

## Caso de Uso { #use-case }

Empecemos con un ejemplo de **caso de uso** y luego veamos cómo resolverlo con esto.

Imaginemos que tienes algunos **modelos de machine learning** que quieres usar para manejar requests. 🤖

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"}

## Use Case { #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. 🤖

## Caso de uso { #use-case }

Vamos começar 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. 🤖

* 100% test coverage: cobertura de tests del 100%
* back and forth: de un lado a otro
* I/O (as in "input and output"): I/O (do not translate to "E/S")
* Machine Learning: Machine Learning (do not translate to "Aprendizaje Automático")
* Deep Learning: Deep Learning (do not translate to "Aprendizaje Profundo")
* callback hell: callback hell (do not translate to "infierno de callbacks")
* tip: Consejo (do not translate to "tip")

{* ../../docs_src/path_params/tutorial005_py39.py hl[1,6:9] *}

/// tip

If you are wondering, "AlexNet", "ResNet", and "LeNet" are just names of Machine Learning <abbr title="Technically, Deep Learning model architectures">models</abbr>.

///

### Declare a *path parameter* { #declare-a-path-parameter }

## TensorFlow models are programs

TensorFlow
[**models**](https://developers.google.com/machine-learning/glossary/#model) (to
use a term commonly used by machine learning practitioners) are expressed as
programs that TensorFlow executes. TensorFlow programs are encoded as
computation
[**graphs**](https://developers.google.com/machine-learning/glossary/#graph).
Since models are practically programs that TensorFlow executes, using untrusted