dltk.networks.super_resolution package

dltk.networks.super_resolution.simple_super_resolution module

dltk.networks.super_resolution.simple_super_resolution.simple_super_resolution_3d(inputs, num_convolutions=1, filters=(16, 32, 64), upsampling_factor=(2, 2, 2), mode='eval', use_bias=False, kernel_initializer=<tensorflow.python.ops.init_ops.VarianceScaling object>, bias_initializer=<tensorflow.python.ops.init_ops.Zeros object>, kernel_regularizer=None, bias_regularizer=None)[source]
Simple super resolution network with num_convolutions per feature
extraction block. Each convolution in a block b has a filter size of filters[b].
Parameters:
  • inputs (tf.Tensor) – Input feature tensor to the network (rank 5 required).
  • num_convolutions (int, optional) – Number of convolutions.
  • filters (tuple, optional) – filters (tuple, optional): Number of filters.
  • upsampling_factor (tuple, optional) – Upsampling factor of the low resolution to the high resolution image.
  • mode (TYPE, optional) – One of the tf.estimator.ModeKeys strings: TRAIN, EVAL or PREDICT
  • use_bias (bool, optional) – Boolean, whether the layer uses a bias.
  • kernel_initializer (TYPE, optional) – An initializer for the convolution kernel.
  • bias_initializer (TYPE, optional) – An initializer for the bias vector. If None, no bias will be applied.
  • kernel_regularizer (None, optional) – Optional regularizer for the convolution kernel.
  • bias_regularizer (None, optional) – Optional regularizer for the bias vector.
Returns:

dictionary of output tensors

Return type:

dict

Module contents