Call this function in your script after you have finished setting all cfg values that are necessary (e.g., merging a config from a file, merging

Checks that `value_a`, which is intended to replace `value_b` is of the right type. The type is correct if it matches exactly or is one of a few

Decodes a raw config value (e.g., from a yaml config files or command line argument) into a Python object.

Return an activation function given a string

Merge config dictionary a into config dictionary b, clobbering the options in b whenever they are also specified in a.

length: B. return B x max_len. If max_len is None, then max of length will be used.

start training iterations

start test iterations

set model, criterion and optimizer

Set immutability to is_immutable and recursively apply the setting to all nested AttrDicts.

load config file into cfg

load config file into cfg

load config file into cfg

Sample the positive pair (i.e., o and o^+) within a character by per-sample shuffling. Per-sample shuffling is done by argsort random

Compute loss for model. If both `labels` and `mask` are None, it degenerates to SimCLR unsupervised loss: https://arxiv.org/pdf/2002.0

Embed inputs. Args: emb (FloatTensor): Sequence of word vectors ``(seq_len, batch_size, self.dim)`` s

Merge `cfg_other` into the global config.

Load a yaml config file and merge it into the global config.