Make a grid of images with space in between. Args: ims: a list of [3, im_h, im_w] images n_rows: num of rows n_cols: num of colu

Returns the stringified extra_repr() of a module.

Normalizing to unit length along the specified dimension. Args: x: pytorch Variable Returns: x: pytorch Variable, same shape as in

Print usage and parse arguments.

Image name format: 0001001.png, where first four digits represent identity and last four digits represent cameras. Camera 1&2 are con

Image name format: 0001001.png, where first four digits represent identity and last four digits represent cameras. Camera 1&2 are con

Image name format: 0001001.png, where first four digits represent identity and last four digits represent cameras. Camera 1&2 are con

Print kernel information. This is used by prof.py.

Args: dist_mat: pytorch Variable, pair wise distance between samples, shape [N, N] labels: pytorch LongTensor, with shape [N]

Removes the given reparameterization of a parameter from a module. If no parameter is supplied then all reparameterizations are removed.

Creates Parameters to be used for reparameterization and creates names that for attributes for the module these Parameters will corre

Call this method to disable sparsity and restore all weights. This will only work if init(...) was called with allow_recompute=True.

resume model from the last one in path self.output_path

resume model from resume_epoch

Revert effect of previously calling partial_step.

save model as save_epoch