R/applications.R
application_inception_resnet_v2.Rd
InceptionResNet v2 model, with weights trained on ImageNet
application_inception_resnet_v2( include_top = TRUE, weights = "imagenet", input_tensor = NULL, input_shape = NULL, pooling = NULL, classes = 1000 ) inception_resnet_v2_preprocess_input(x)
include_top  whether to include the fullyconnected layer at the top of the network. 

weights 

input_tensor  optional Keras tensor to use as image input for the model. 
input_shape  optional shape list, only to be specified if 
pooling  Optional pooling mode for feature extraction when

classes  optional number of classes to classify images into, only to be
specified if 
x  Input tensor for preprocessing 
A Keras model instance.
Do note that the input image format for this model is different than for the VGG16 and ResNet models (299x299 instead of 224x224).
The inception_resnet_v2_preprocess_input()
function should be used for image
preprocessing.
Inceptionv4, InceptionResNet and the Impact of Residual Connections on Learning(https://arxiv.org/abs/1512.00567)