Evaluation Utils (radionets.evaluatuion.utils)

Evaluation utils submodule of radionets.evaluation.

Reference/API

radionets.evaluation.utils Module

Functions

apply_normalization(img_test, norm_dict)	Applies one of currently two normalization methods if the training was normalized
apply_symmetry(img_dict)	Pads and applies symmetry to half images.
check_outpath(model_path)	Checks if there is already a predictions file in the evaluation folder
check_samp_file(eval_conf)	Checks if a file with sampled images is located in the evaluation folder
check_vmin_vmax(inp)	Check wether the absolute of the maxmimum or the minimum is bigger.
create_databunch(data_path, fourier, ...)	Create a dataloader object, which feeds the data batch-wise
create_sampled_databunch(data_path, batch_size)	Create a dataloader object, which feeds the data batch-wise
eval_model(img, model)	Put model into eval mode and evaluate test images.
get_ifft(array[, amp_phase, scale])	Compute the inverse Fourier transformation
get_images(test_ds, num_images[, rand, indices])	Get n random test and truth images or mean, standard deviation and true images from an already sampled dataset.
load_data(data_path, mode[, fourier])	Load data set from a directory and return it as H5DataSet.
load_pre_model(learn, pre_path[, visualize, ...])	Loads a previously saved model as pre-model.
load_pretrained_model(arch_name, model_path)	Load model architecture and pretrained weigths.
make_axes_nice(fig, ax, im, title[, phase, ...])	Create nice colorbars with bigger label size for every axis in a subplot.
mergeDictionary(dict_1, dict_2)
preprocessing(conf)	Makes the necessary preprocessing for the evaluation methods analyzing the whole test dataset.
process_prediction(conf, img_test, img_true, ...)	Applies the normalization, gets and rescales a prediction and performs the inverse Fourier transformation.
read_config(config)	Parse the toml config file
read_pred(path)	Read data saved with save_pred from h5 file.
rescale_normalization(pred, norm_dict)	Rescale the prediction after normalized training
reshape_2d(array)	Reshape 1d arrays into 2d ones.
sample_images(mean, std, num_samples, conf)	Samples for every pixel in Fourier space from a truncated Gaussian distribution based on the output of the network.
save_pred(path, img)	Write test data and predictions to h5 file.
set_num_threads(n)	Set the number of threads to use for parallel execution.
source_list_collate(batch)	Collate function for the DataLoader with source list
symmetry(image, key)	Symmetry function to complete the images.
trunc_rvs(mu, sig, num_samples, mode[, ...])
vectorize([ftylist_or_function, target, ...])	A decorator that creates a NumPy ufunc object using Numba compiled code.

Classes

DataLoader(dataset[, batch_size, shuffle, ...])	Data loader combines a dataset and a sampler, and provides an iterable over the given dataset.
Path(*args, **kwargs)	PurePath subclass that can make system calls.
sampled_dataset(bundle_path)

Class Inheritance Diagram