Visualizing Filters of a CNN using TensorFlow

4.6
estrelas
20 classificações
oferecido por
Coursera Project Network
Neste Projeto Guiado gratuito, você irá:

Implement gradient ascent algorithm

Visualize image features that maximally activate filters of a CNN

Mostre essa experiência prática em uma entrevista

Clock1 hour
IntermediateIntermediário
CloudSem necessidade de download
VideoVídeo em tela dividida
Comment DotsInglês
LaptopApenas em desktop

In this short, 1 hour long guided project, we will use a Convolutional Neural Network - the popular VGG16 model, and we will visualize various filters from different layers of the CNN. We will do this by using gradient ascent to visualize images that maximally activate specific filters from different layers of the model. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment which is a fantastic tool for creating and running Jupyter Notebooks in the cloud, and Colab even provides free GPUs for your notebooks. You will need prior programming experience in Python. 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 the TensorFlow to visualize various filters of a CNN. 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.

Requisitos

Prior experience in Python, theoretical understanding of Convolutional Neural Networks and optimization algorithms like gradient descent.

Habilidades que você desenvolverá

Deep LearningArtificial Neural NetworkConvolutional Neural NetworkMachine LearningTensorflow

Aprender passo a passo

Em um vídeo reproduzido em uma tela dividida com a área de trabalho, seu instrutor o orientará sobre esses passos:

  1. Introduction

  2. Downloading the Model

  3. Get Submodels

  4. Image Visualization

  5. Training Loop

  6. Final Results

Como funcionam os projetos guiados

Sua área de trabalho é um espaço em nuvem, acessado diretamente do navegador, sem necessidade de nenhum download

Em um vídeo de tela dividida, seu instrutor te orientará passo a passo

Perguntas Frequentes – FAQ

Perguntas Frequentes – FAQ

Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.