U-Net ResNet34¶

class src.pipelines.tensorflow_v2.models.unet_resnet.ResBlock(*args, **kwargs)[source]¶

A Residual block

call(x)[source]¶

Applies a ResBlock to the an input

Parameters: x (Tensor) – the input to apply the ResBlock to
Return type: Tensor
Returns: the output of the ResBlock

class src.pipelines.tensorflow_v2.models.unet_resnet.UnetResnet(output_channels, activation='relu', initializer='he_normal', filters=3)[source]¶

A U-Net model, which has a ResNet 34 backbone

call(x)[source]¶

Applies a U-Net ResNet34 model to the input.

Parameters: inputs – an input image
Return type: Tensor
Returns: the output of a U-Net ResNet34 model

model(shape=(512, 512, 1))[source]¶

Returns a U-Net model as tf.keras.Model. This is a workaround to use the functional api, which allows the model to be viewed.

Parameters: shape (Tuple[int, int, int]) – the shape of the input
Return type: Model
Returns: the tf.keras.Model instantiated using the functional api

print_all_layers()[source]¶

Prints all the layers in the model, including the layers in the subclasses which make up the model. This uses the model() workaround function.

Return type: None
Returns: None

get_all_layers()[source]¶

Returns all the layers in the model, including the layers in the subclasses which make up the model. This uses the model() workaround function.

Return type: List[Layer]
Returns: a list of layers