Enable javascript in your browser for better experience. Need to know to enable it? Go here.
As informações desta página não estão completamente disponíveis no seu idioma de escolha. Esperamos disponibiliza-las integralmente em outros idiomas em breve. Para ter acesso às informações no idioma de sua preferência, faça o download do PDF aquí.
Atualizado em : May 15, 2018
NÃO ENTROU NA EDIÇÃO ATUAL
Este blip não está na edição atual do Radar. Se esteve em uma das últimas edições, é provável que ainda seja relevante. Se o blip for mais antigo, pode não ser mais relevante e nossa avaliação pode ser diferente hoje. Infelizmente, não conseguimos revisar continuamente todos os blips de edições anteriores do Radar. Saiba mais
May 2018
Avalie ? Vale a pena explorar com o objetivo de compreender como isso afetará sua empresa.

Machine-learning models are starting to creep into everyday business applications. When enough training data is available, these algorithms can address problems that might have previously required complex statistical models or heuristics. As we move from experimental use to production, we need a reliable way to host and deploy the models that can be accessed remotely and scale with the number of consumers. TensorFlow Serving addresses part of that problem by exposing a remote gRPC interface to an exported model; this allows a trained model to be deployed in a variety of ways. TensorFlow Serving also accepts a stream of models to incorporate continuous training updates, and its authors maintain a Dockerfile to ease the deployment process. Presumably, the choice of gRPC is to be consistent with the TensorFlow execution model; however, we’re generally wary of protocols that require code generation and native bindings.

Nov 2017
Avalie ? Vale a pena explorar com o objetivo de compreender como isso afetará sua empresa.

Machine-learning models are starting to creep into everyday business applications. When enough training data is available, these algorithms can address problems that might have previously required complex statistical models or heuristics. As we move from experimental use to production, we need a reliable way to host and deploy the models that can be accessed remotely and scale with the number of consumers. TensorFlow Serving addresses part of that problem by exposing a remote gRPC interface to an exported model; this allows a trained model to be deployed in a variety of ways. TensorFlow Serving also accepts a stream of models to incorporate continuous training updates, and its authors maintain a Dockerfile to ease the deployment process. Presumably, the choice of gRPC is to be consistent with the TensorFlow execution model; however, we’re generally wary of protocols that require code generation and native bindings.

Publicado : Nov 30, 2017
Radar

Baixar o Technology Radar Volume 26

English | Español | Português | 中文

Radar

Mantenha-se por dentro das tendências de tecnologia

 

Seja assinante

Visite nosso arquivo para acessar os volumes anteriores