There is an application module in Keras that provides a pre-trained model for creating deep neural networks. The pre-trained models consist of two parts Architecture and model Weights. Some popular pre-trained models include:
- VGG16
- MobileNet
- InceptionV3
- ResNet
- InceptionResNetV2
You can easily load a model with the help of the following code:
import keras
import numpy as np
from keras.applications import vgg16, inception_v3, resnet50, mobilenet
vgg_m = vgg16.VGG16(weights = 'imagenet')
model_inception = inception_v3.InceptionV3(weights = 'imagenet')
#Load the ResNet50 model
model_resnet = resnet50.ResNet50(weights = 'imagenet')
After the model is successfully loaded, you can immediately use it to check the prediction.