Build the whole model architecture, defined by ``cfg.MODEL.META_ARCHITECTURE``. Note that it does not load any weights from ``cfg``.

Build an optimizer from config.

Delete all the stored histograms for visualization. This should be called after histograms are written to tensorboard.

Delete all the stored images for visualization. This should be called after images are written to tensorboard.

Apply some basic name conversion to names in C2 weights. It only deals with typical backbone models. Args: original_keys (l

Map Caffe2 Detectron weight names to Detectron2 names. Args: weights (dict): name -> tensor Returns: dict: detec

Takes a list of reference sentences for a single segment and returns an object that encapsulates everything that BLEU needs to know about them

Takes a list of reference sentences for a single segment and returns an object that encapsulates everything that BLEU needs to know about th

Takes a test sentence and returns an object that encapsulates everything that BLEU needs to know about it. :param test: list of string : hyp

Create a parser with some common arguments used by X-modaler users. Args: epilog (str): epilog passed to ArgumentParser describing t

Perform some basic common setups at the beginning of a job, including: 1. Set up the X-modaler logger 2. Log basic information about env

Build a list of :class:`EventWriter` to be used. It now consists of a :class:`CommonMetricPrinter`, :class:`TensorboardXWriter` and :clas

Downgrade a config from its current version to an older version. Args: cfg (CfgNode): to_version (int): Note: A

encode captions of the same video into one 2-D array, also produces a dict to point out the array based on image id

encode captions of the same video into one 2-D array, also produces a dict to point out the array based on image id

Expand a hierarchical dict of scalars into a flat dict of scalars. If results[k1][k2][k3] = v, the returned dict will have the entry {

Look for keys with the following patterns: 1) Starts with "fpn.inner." Example: "fpn.inner.res2.2.sum.lateral.weight"

Get a copy of the default config. Returns: a X-modaler CfgNode instance.

Guess the version of a partial config where the VERSION field is not specified. Returns the version, or the latest if cannot make a guess.

Returns: dict[name -> HistoryBuffer]: the HistoryBuffer for all scalars

Returns: dict[str -> (float, int)]: mapping from the name of each scalar to the most recent value and the iterati

Launch multi-gpu or distributed training. This function must be called on all machines involved in the training. It will spawn child proc

Load a list of (path,image_id tuples). Modify this to suit your data locations.

Loads a vocabulary file into a dictionary.

Parse input arguments