Creating Multi Task Models With Keras

4.8
étoiles
28 évaluations
Offert par
Coursera Project Network
Dans ce Projet guidé gratuit, vous :

Creating multi-task models with Keras

Training multi-task models with Keras

Mettez en valeur cette expérience pratique dans un entretien

Clock2 hours
IntermediateIntermédiaire
CloudAucun téléchargement requis
VideoVidéo en écran partagé
Comment DotsAnglais
LaptopOrdinateur de bureau uniquement

In this 1 hour long guided project, you will learn to create and train multi-task, multi-output models with Keras. You will learn to use Keras' functional API to create a multi output model which will be trained to learn two different labels given the same input example. The model will have one input but two outputs. A few of the shallow layers will be shared between the two outputs, you will also use a ResNet style skip connection in the model. If you are familiar with Keras, you have probably come across examples of models that are trained to perform multiple tasks. For example, an object detection model where a CNN is trained to find all class instances in the input images as well as give a regression output to localize the detected class instances in the input. Being able to use Keras' functional API is a first step towards building complex, multi-output models like object detection models. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment. You will need prior programming experience in Python. You will also need prior experience with Keras. Consider this to be an intermediate level Keras project. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like gradient descent but want to understand how to use use Keras to write custom, more complex models than just plain sequential neural networks. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Conditions

Prior programming experience in Python. Conceptual understanding of Neural Networks. Prior experience with TensorFlow and Keras is recommended.

Les compétences que vous développerez

Deep LearningMachine LearningTensorflowComputer Visionkeras

Apprendrez étape par étape

Votre enseignant(e) vous guidera étape par étape, grâce à une vidéo en écran partagé sur votre espace de travail :

  1. Introduction

  2. Create Dataset

  3. Dataset Generator

  4. Create Model

  5. Train the Model

  6. Final Predictions

Comment fonctionnent les projets guidés

Votre espace de travail est un bureau cloud situé dans votre navigateur, aucun téléchargement n'est requis.

Votre enseignant(e) vous guide étape par étape dans une vidéo en écran partagé

Avis

Meilleurs avis pour CREATING MULTI TASK MODELS WITH KERAS

Voir tous les avis

Foire Aux Questions

Foire Aux Questions

D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.