Keras Tutorial
Selected Reading
- Keras - Discussion
- Keras - Useful Resources
- Keras - Quick Guide
- Keras - Pre-Trained Models
- Keras - Real Time Prediction using ResNet Model
- Keras - Applications
- Keras - Time Series Prediction using LSTM RNN
- Keras - Regression Prediction using MPL
- Keras - Convolution Neural Network
- Keras - Model Evaluation and Prediction
- Keras - Model Compilation
- Keras - Models
- Keras - Customized Layer
- Keras - Layers
- Keras - Modules
- Keras - Deep learning
- Keras - Overview of Deep learning
- Keras - Backend Configuration
- Keras - Installation
- Keras - Introduction
- Keras - Home
Selected Reading
- Who is Who
- Computer Glossary
- HR Interview Questions
- Effective Resume Writing
- Questions and Answers
- UPSC IAS Exams Notes
Keras - Applications
Keras - Apppcations
Keras apppcations module is used to provide pre-trained model for deep neural networks. Keras models are used for prediction, feature extraction and fine tuning. This chapter explains about Keras apppcations in detail.
Pre-trained models
Trained model consists of two parts model Architecture and model Weights. Model weights are large file so we have to download and extract the feature from ImageNet database. Some of the popular pre-trained models are psted below,
ResNet
VGG16
MobileNet
InceptionResNetV2
InceptionV3
Loading a model
Keras pre-trained models can be easily loaded as specified below −
import keras import numpy as np from keras.apppcations import vgg16, inception_v3, resnet50, mobilenet #Load the VGG model vgg_model = vgg16.VGG16(weights = imagenet ) #Load the Inception_V3 model inception_model = inception_v3.InceptionV3(weights = imagenet ) #Load the ResNet50 model resnet_model = resnet50.ResNet50(weights = imagenet ) #Load the MobileNet model mobilenet_model = mobilenet.MobileNet(weights = imagenet )
Once the model is loaded, we can immediately use it for prediction purpose. Let us check each pre-trained model in the upcoming chapters.
Advertisements