Model prints with number of trainable parameters

Training logic for an epoch :param epoch: Current training epoch. :return: A log that contains all information you want to s

Inception block

Feature gating as used in S3D-G.

Defines the S3DG base architecture.

Aggregates feature maps into a fixed size representation. In the following notation, B = batch_size, N = num_features, K = num_clusters, D =

Forward pass of the function.

Compute joint embeddings and, if requested, a confusion matrix between video and text representations in the minibatch. Notation: B =

Forward pass logic :return: Model output

Return the directory that stores images

wrapper function for endless data loader.

create empty directories if they don't exist Parameters: paths (str list) -- a list of directory paths

Print the mean, min, max, median, std, and size of a numpy array Parameters: val (bool) -- if print the values of the numpy array

Resets the meter to default settings.

Compute classification metrics from a similiarity matrix.