ImageNet is an image database organized according to the WordNet hierarchy (currently only the nouns), in which each node of the hierarchy is depicted by hundreds and thousands of images. (cite: http://www.image-net.org)
Models in Convolutional neural network (CNN) for image classification with weights trained on ImageNet such as:
- Xception
- VGG16
- VGG19
- ResNet50
- InceptionV3
These models are supported in Keras and this example shows to use them
-
Xception: Deep Learning with Depthwise Separable Convolutions https://arxiv.org/abs/1610.02357 (Xception model)
-
Very Deep Convolutional Networks for Large-Scale Image Recognition https://arxiv.org/abs/1409.1556 (VGG models)
-
Deep Residual Learning for Image Recognition https://arxiv.org/abs/1512.03385 ( ResNet model)
-
Rethinking the Inception Architecture for Computer Vision https://arxiv.org/abs/1512.00567 ( Inception v3 model )