neural_de.external.maxim_tf package

Subpackages

• neural_de.external.maxim_tf.maxim package
  • Subpackages
    • neural_de.external.maxim_tf.maxim.blocks package
      • Submodules
      • neural_de.external.maxim_tf.maxim.blocks.attentions module
      • neural_de.external.maxim_tf.maxim.blocks.block_gating module
      • neural_de.external.maxim_tf.maxim.blocks.bottleneck module
      • neural_de.external.maxim_tf.maxim.blocks.grid_gating module
      • neural_de.external.maxim_tf.maxim.blocks.misc_gating module
      • neural_de.external.maxim_tf.maxim.blocks.others module
      • neural_de.external.maxim_tf.maxim.blocks.unet module
      • Module contents
  • Submodules
  • neural_de.external.maxim_tf.maxim.configs module
  • neural_de.external.maxim_tf.maxim.layers module
    • BlockImages
      • BlockImages.call()
      • BlockImages.get_config()
    • Resizing
      • Resizing.call()
      • Resizing.get_config()
    • SwapAxes
      • SwapAxes.call()
      • SwapAxes.get_config()
    • UnblockImages
      • UnblockImages.call()
      • UnblockImages.get_config()
  • neural_de.external.maxim_tf.maxim.maxim module
    • MAXIM()
    • features
    • depth
    • num_stages
    • num_groups
    • use_bias
    • num_supervision_scales
    • lrelu_slope
    • use_global_mlp
    • use_cross_gating
    • high_res_stages
    • block_size_hr
    • block_size_lr
    • grid_size_hr
    • grid_size_lr
    • num_bottleneck_blocks
    • block_gmlp_factor
    • grid_gmlp_factor
    • input_proj_factor
    • channels_reduction
    • num_outputs
    • dropout_rate
  • Module contents

Submodules

neural_de.external.maxim_tf.create_maxim_model module

Model class

neural_de.external.maxim_tf.create_maxim_model.Model(variant=None, input_resolution=(256, 256), **kw)

Factory function to easily create a Model variant like “S”.

Parameters:

• variant – UNet model variants. Options: ‘S-1’ | ‘S-2’ | ‘S-3’ | ‘M-1’ | ‘M-2’ | ‘M-3’

• input_resolution – Size of the input images.

• **kw – Other UNet config dicts.

Return type:

Model

Returns:

The MAXIM model.

Module contents

Contains code from the Tensorflow implementation of Maxim from https://github.com/sayakpaul/maxim-tf.