Creating Multi Task Models With Keras

4.7
estrellas
33 calificaciones
ofrecido por
Coursera Project Network
En este Proyecto guiado gratis, tú:

Creating multi-task models with Keras

Training multi-task models with Keras

Demuestra esta experiencia práctica en una entrevista

Clock2 hours
IntermediateIntermedio
CloudNo se necesita descarga
VideoVideo de pantalla dividida
Comment DotsInglés (English)
LaptopSolo escritorio

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.

Requerimientos

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

Habilidades que desarrollarás

Deep LearningMachine LearningTensorflowComputer Visionkeras

Aprende paso a paso

En un video que se reproduce en una pantalla dividida con tu área de trabajo, tu instructor te guiará en cada paso:

  1. Introduction

  2. Create Dataset

  3. Dataset Generator

  4. Create Model

  5. Train the Model

  6. Final Predictions

Cómo funcionan los proyectos guiados

Tu espacio de trabajo es un escritorio virtual directamente en tu navegador, no requiere descarga.

En un video de pantalla dividida, tu instructor te guía paso a paso

Reseñas

Principales reseñas sobre CREATING MULTI TASK MODELS WITH KERAS

Ver todas las reseñas

Preguntas Frecuentes

Preguntas Frecuentes

¿Tienes más preguntas? Visita el Centro de Ayuda al Alumno.