One Article Review
| Source |  CodingSec |
|---|---|
| Identifiant | 360580 |
| Date de publication | 2017-05-01 14:46:11 (vue: 2017-05-01 14:46:11) |
| Titre | How to build a basic Data Graph in Tensor Flow |
| Texte | TensorFlow is a programming system in which you represent computation as graph. Node in the graph is called op (short for operations). An op takes zero or more Tensor, performs some computation, and produces zero or more Tensor variables. A Tensor is a typed multi-dimensional array. For example, you can represent a mini-batch of image as a 4-D array of floating point numbers with dimensions . A TensorFlow graphs is a description of computation. To compute anything, a graph must be launched in a Sessions. A Session places the graph ops onto Device, such as CPUs or GPUs, |
| Envoyé | Oui |
| Condensat | anything appeared array basic batch build called can coding computation compute cpus data description device dimensional dimensions example first floating flow gpus graph graphs how image launched mini more multi must node numbers onto operations ops opâ performs places point post produces programming represent security session sessions short some such system takes tensor tensorflow typed variables which zero |
| Tags | |
| Stories | |
| Notes | |
| Move | 
|
L'article ne semble pas avoir été repris aprés sa publication.
L'article ne semble pas avoir été repris sur un précédent.