Return a learning rate scheduler Parameters: optimizer -- the optimizer of the network opt (option class) -- stores all

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

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new model-specific options, and rewrite default values for existing options. Parameters: parser -- original option p

Add new dataset-specific options, and rewrite default values for existing options. Parameters: parser -- original option

Add new model-specific options and rewrite default values for existing options. Parameters: parser -- the option parser

Calculate losses, gradients, and update network weights; called in every training iteration

Calculate losses, gradients, and update network weights; called in every training iteration

Update network weights; it will be called in every training iteration.

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

resize the lane from Size(curr_width, curr_height) to Size(im_width, im_height)

Save a numpy image to the disk Parameters: image_numpy (numpy array) -- input numpy array image_path (str) -- the path o

Unpack input data from the dataloader and perform necessary pre-processing steps. Parameters: input (dict): include the data itse

Unpack input data from the dataloader and perform necessary pre-processing steps. Parameters: input (dict): includes the data its

Unpack input data from the dataloader and perform necessary pre-processing steps. Parameters: input: a dictionary that contains t

Converts a Tensor array into a numpy image array. Parameters: input_image (tensor) -- the input image tensor array imtype (type)

Override the default train() to freeze the BN parameters :return: