unet: U-Net: Convolutional Networks for Biomedical Image...

In r-tensorflow/unet: U-Net: Convolutional Networks for Biomedical Image Segmentation

Description

U-Net: Convolutional Networks for Biomedical Image Segmentation

Usage

unet(input_shape, num_classes = 1, dropout = 0.5, filters = 64,
  num_layers = 4, output_activation = "sigmoid")

Arguments

input_shape	Dimensionality of the input (integer) not including the samples axis. Must be lenght 3 numeric vector.
num_classes	Number of classes.
dropout	Dropout rate applied.
filters	Number of filters of the first convolution.
num_layers	Number of layers in the encoder.
output_activation	Activation in the output layer.

r-tensorflow/unet documentation built on Nov. 5, 2019, 2:06 a.m.