sup3r.models.abstract.AbstractInterface

class AbstractInterface

Bases: ABC

Abstract class to define the required interface for Sup3r model subclasses

Note that this only sets the required interfaces for a GAN that can be loaded from disk and used to predict synthetic outputs. The interface for models that can be trained will be set in another class.

Methods

generate(low_res[, norm_in, un_norm_out, ...])	Use the generator model to generate high res data from low res input.
get_s_enhance_from_layers()	Compute factor by which model will enhance spatial resolution from layer attributes.
get_t_enhance_from_layers()	Compute factor by which model will enhance temporal resolution from layer attributes.
load(model_dir[, verbose])	Load the GAN with its sub-networks from a previously saved-to output directory.
save_params(out_dir)
seed([s])	Set the random seed for reproducible results.
set_model_params(**kwargs)	Set parameters used for training the model

Attributes

hr_exo_features	Get list of high-resolution exogenous filter names the model uses.
hr_out_features	Get the list of high-resolution output feature names that the generative model outputs.
input_dims	Get dimension of model generator input.
input_resolution	'...km', 'temporal': '...min'}.
is_4d	Check if model expects spatial only input
is_5d	Check if model expects spatiotemporal input
lr_features	Get a list of low-resolution features input to the generative model.
meta	Get meta data dictionary that defines how the model was created
model_params	Model parameters, used to save model to disc
output_resolution	Resolution of output data.
s_enhance	Factor by which model will enhance spatial resolution.
smoothed_features	Get the list of smoothed input feature names that the generative model was trained on.
smoothing	Value of smoothing parameter used in gaussian filtering of coarsened high res data.
t_enhance	Factor by which model will enhance temporal resolution.
version_record	A record of important versions that this model was built with.

abstract classmethod load(model_dir, verbose=True)

Load the GAN with its sub-networks from a previously saved-to output directory.

Parameters:

• model_dir – Directory to load GAN model files from.

• verbose (bool) – Flag to log information about the loaded model.

Returns:

out (BaseModel) – Returns a pretrained gan model that was previously saved to model_dir

abstract generate(low_res, norm_in=True, un_norm_out=True, exogenous_data=None)

Use the generator model to generate high res data from low res input. This is the public generate function.

static seed(s=0)

Set the random seed for reproducible results.

Parameters:

s (int) – Random seed

property input_dims

Get dimension of model generator input. This is usually 4D for spatial models and 5D for spatiotemporal models. This gives the input to the first step if the model is multi-step. Returns 5 for linear models.

Returns:

int

property is_5d

Check if model expects spatiotemporal input

property is_4d

Check if model expects spatial only input

get_s_enhance_from_layers()

Compute factor by which model will enhance spatial resolution from layer attributes. Used in model training during high res coarsening

get_t_enhance_from_layers()

Compute factor by which model will enhance temporal resolution from layer attributes. Used in model training during high res coarsening

property s_enhance

Factor by which model will enhance spatial resolution. Used in model training during high res coarsening

property t_enhance

Factor by which model will enhance temporal resolution. Used in model training during high res coarsening

property input_resolution

‘…km’, ‘temporal’: ‘…min’}. The numbers are required to be integers in the units specified. The units are not strict as long as the resolution of the exogenous data, when extracting exogenous data, is specified in the same units.

Type:

Resolution of input data. Given as a dictionary {‘spatial’

property output_resolution

Resolution of output data. Given as a dictionary {‘spatial’: ‘…km’, ‘temporal’: ‘…min’}. This is computed from the input resolution and the enhancement factors.

abstract property meta

Get meta data dictionary that defines how the model was created

property lr_features

Get a list of low-resolution features input to the generative model. This includes low-resolution features that might be supplied exogenously at inference time but that were in the low-res batches during training

property hr_out_features

Get the list of high-resolution output feature names that the generative model outputs.

property hr_exo_features

Get list of high-resolution exogenous filter names the model uses. If the model has N concat or add layers this list will be the last N features in the training features list. The ordering is assumed to be the same as the order of concat or add layers. If training features is […, topo, sza], and the model has 2 concat or add layers, exo features will be [topo, sza]. Topo will then be used in the first concat layer and sza will be used in the second

property smoothing

Value of smoothing parameter used in gaussian filtering of coarsened high res data.

property smoothed_features

Get the list of smoothed input feature names that the generative model was trained on.

property model_params

Model parameters, used to save model to disc

Returns:

dict

property version_record

A record of important versions that this model was built with.

Returns:

dict

set_model_params(**kwargs)

Set parameters used for training the model

Parameters:

kwargs (dict) – Keyword arguments including ‘input_resolution’, ‘lr_features’, ‘hr_exo_features’, ‘hr_out_features’, ‘smoothed_features’, ‘s_enhance’, ‘t_enhance’, ‘smoothing’

save_params(out_dir)

Parameters:

out_dir (str) – Directory to save linear model params. This directory will be created if it does not already exist.