unet

UNET implementations.

Functions

FUNet

Functional UNET Implementation.

Classes

SUNet	Semantic UNet.
UNet	UNet Architecture.

ashpy.models.convolutional.unet.FUNet(input_res, min_res, kernel_size, initial_filters, filters_cap, channels, input_channels=3, use_dropout_encoder=True, use_dropout_decoder=True, dropout_prob=0.3, encoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.LeakyReLU'>, decoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.ReLU'>, last_activation=<function tanh>, use_attention=False)

Functional UNET Implementation.

class ashpy.models.convolutional.unet.SUNet(input_res, min_res, kernel_size, initial_filters, filters_cap, channels, use_dropout_encoder=True, use_dropout_decoder=True, dropout_prob=0.3, encoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.LeakyReLU'>, decoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.ReLU'>, use_attention=False)

Bases: ashpy.models.convolutional.unet.UNet

Semantic UNet.

__init__(input_res, min_res, kernel_size, initial_filters, filters_cap, channels, use_dropout_encoder=True, use_dropout_decoder=True, dropout_prob=0.3, encoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.LeakyReLU'>, decoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.ReLU'>, use_attention=False)

Build the Semantic UNet model.

class ashpy.models.convolutional.unet.UNet(input_res, min_res, kernel_size, initial_filters, filters_cap, channels, use_dropout_encoder=True, use_dropout_decoder=True, dropout_prob=0.3, encoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.LeakyReLU'>, decoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.ReLU'>, normalization_layer=<class 'ashpy.layers.instance_normalization.InstanceNormalization'>, last_activation=<function tanh>, use_attention=False)

Bases: ashpy.models.convolutional.interfaces.Conv2DInterface

UNet Architecture.

Architecture similar to the one found in “Image-to-Image Translation with Conditional Adversarial Nets” [1].

Originally proposed in “U-Net: Convolutional Networks for Biomedical Image Segmentation” [2].

Examples

• Direct Usage:

  x = tf.ones((1, 512, 512, 3))
  u_net = UNet(input_res = 512,
               min_res=4,
               kernel_size=4,
               initial_filters=64,
               filters_cap=512,
               channels=3)
  y = u_net(x)
  print(y.shape)
  print(len(u_net.trainable_variables)>0)
  

  (1, 512, 512, 3)
  True
  

[1]	Image-to-Image Translation with Conditional Adversarial Nets - https://arxiv.org/abs/1611.07004

[2]	U-Net: Convolutional Networks for Biomedical Image Segmentation - https://arxiv.org/abs/1505.04597

__init__(input_res, min_res, kernel_size, initial_filters, filters_cap, channels, use_dropout_encoder=True, use_dropout_decoder=True, dropout_prob=0.3, encoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.LeakyReLU'>, decoder_non_linearity=<class 'tensorflow.python.keras.layers.advanced_activations.ReLU'>, normalization_layer=<class 'ashpy.layers.instance_normalization.InstanceNormalization'>, last_activation=<function tanh>, use_attention=False)

Initialize the UNet.

Parameters:

• input_res (int) – input resolution.
• min_res (int) – minimum resolution reached after decode.
• kernel_size (int) – kernel size used in the network.
• initial_filters (int) – number of filter of the initial convolution.
• filters_cap (int) – maximum number of filters.
• channels (int) – number of output channels.
• use_dropout_encoder (bool) – whether to use dropout in the encoder module.
• use_dropout_decoder (bool) – whether to use dropout in the decoder module.
• dropout_prob (float) – probability of dropout.
• encoder_non_linearity (Type[Layer]) – non linearity of encoder.
• decoder_non_linearity (Type[Layer]) – non linearity of decoder.
• last_activation (<module 'tensorflow_core.keras.activations' from '/home/docs/checkouts/readthedocs.org/user_builds/ashpy/envs/master/lib/python3.7/site-packages/tensorflow_core/python/keras/api/_v2/keras/activations/__init__.py'>) – last activation function, tanh or softmax (for semantic images).
• use_attention (bool) – whether to use attention.

call(inputs, training=False)

Forward pass of the UNet model.

get_decoder_block(filters, use_bn=True, use_dropout=False, use_attention=False)

Return a block to be used in the decoder part of the UNET.

Parameters:

• filters – number of filters
• use_bn – whether to use batch normalization
• use_dropout – whether to use dropout
• use_attention – whether to use attention

Returns:

A block to be used in the decoder part

get_encoder_block(filters, use_bn=True, use_attention=False)

Return a block to be used in the encoder part of the UNET.

Parameters:

• filters – number of filters.
• use_bn – whether to use batch normalization.
• use_attention – whether to use attention.

Returns:

A block to be used in the encoder part.