ParseKeywords */

Import */

ObjectToMemviewSlice */

/path/to/log_file.txt

Generator expression that iterates over the params owned by ``optimizer``. Args: optimizer: An optimizer previously returned from ``

recursively fetches (possible) child module and name of weight to be reparameterized

init_hidden()

Call this method to modify your model to take advantage of sparse matrix multiplication. Note that this call alone only augments the model wit

Call this method to monkey patch optimizer step function so that masks can be applied to gradients and weights during training. You mu

Returns the state of the scheduler as a :class:`dict`. It contains an entry for every variable in self.__dict__ which is not the opti

compute cosine distance between two matrix x and y with size (n1, d) and (n2, d) and type torch.tensor return a matrix (n1, n2)

compute euclidean distance between two matrix x and y with size (n1, d) and (n2, d) and type torch.tensor return a matrix (n1, n2)

:class:`toRNNBackend`

combine more than one samples (e.g. market.train and duke.train) as a samples

ObjectToMemviewSlice */

RaiseNeedMoreValuesToUnpack */

RaiseTooManyValuesToUnpack */

decode_c_string */

Return correctly formatted lr/momentum for each param group.

load person reid data_loader from images_folder and uniformly sample according to class for continual

reorder labels map labels [1, 3, 5, 7] to [0,1,2,3]

Delete rows from the temporary SQL table which are no longer required. This speeds up future queries.

:param set1: np.array, 1d :param set2: np.array, 1d :return:

Initializes an image dataset.

It is expected that all threads in the CTA enter this function!

normalize a 2d matrix along axis 1

reset_parameters()