Calculate clustering accuracy. Require scikit-learn installed # Arguments y: true labels, numpy.array with shape `(n_samples,)`

Given a list of evaluation functions to use (e.g ['v1', 'v2']) evaluate and log ACC results :param y_true: GT labels :param y_pred: Pred

:return: train_dataset: MergedDataset which concatenates labelled and unlabelled test_dataset, unlabelled_train_example

/path/to/log_file.txt

In this case, the test loader needs to have the labelled and unlabelled subsets of the training data

Returns a function that maps each index in 0, 1, ..., n-1 to a distinct RGB color; the keyword argument name must be a standard mpl colormap name.

In this case, the test loader needs to have the labelled and unlabelled subsets of the training data

return current time in format of 2000-01-01 12:01:01

Resets num_bad_epochs counter and cooldown counter.

Outputs a function which will log the arguments to Visdom in an appropriate way. Args: vis_fn: A function, such as self.

r''' using broadcast mechanism to calculate pairwise ecludian distance of data the input data is N*M matrix, where M is the dimension we f

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

Computes the accuracy over the k top predictions for the specified values of k

Computes the accuracy over the k top predictions for the specified values of k

基于infomap的聚类 :param nbrs: :param dists: :param pred_label_path: :return:

Download the FGVC-Aircraft data if it doesn't exist already.