kpick.classifier.classification_utils package

Subpackages

Submodules

kpick.classifier.classification_utils.eval module

kpick.classifier.classification_utils.eval.accuracy(output, target, topk=(1,))

Computes the precision@k for the specified values of k

kpick.classifier.classification_utils.logger module

class kpick.classifier.classification_utils.logger.Logger(fpath, title=None, resume=False)

Bases: object

Save training process to log file with simple plot function.

append(numbers)
close()
plot(names=None)
set_names(names)
class kpick.classifier.classification_utils.logger.LoggerMonitor(paths)

Bases: object

Load and visualize multiple logs.

plot(names=None)
kpick.classifier.classification_utils.logger.savefig(fname, dpi=None)

kpick.classifier.classification_utils.misc module

Some helper functions for PyTorch, including: - get_mean_and_std: calculate the mean and std value of dataset. - msr_init: net parameter initialization. - progress_bar: progress bar mimic xlua.progress.

class kpick.classifier.classification_utils.misc.AverageMeter

Bases: object

Computes and stores the average and current value Imported from https://github.com/pytorch/examples/blob/master/imagenet/main.py#L247-L262

reset()
update(val, n=1)
kpick.classifier.classification_utils.misc.get_mean_and_std(dataset)

Compute the mean and std value of dataset.

kpick.classifier.classification_utils.misc.init_params(net)

Init layer parameters.

kpick.classifier.classification_utils.misc.mkdir_p(path)

make dir if not exist

kpick.classifier.classification_utils.visualize module

kpick.classifier.classification_utils.visualize.make_image(img, mean=(0, 0, 0), std=(1, 1, 1))
kpick.classifier.classification_utils.visualize.show_batch(images, Mean=(2, 2, 2), Std=(0.5, 0.5, 0.5))
kpick.classifier.classification_utils.visualize.show_mask(images, masklist, Mean=(2, 2, 2), Std=(0.5, 0.5, 0.5))
kpick.classifier.classification_utils.visualize.show_mask_single(images, mask, Mean=(2, 2, 2), Std=(0.5, 0.5, 0.5))

Module contents

Useful utils