why to implement x=deepcopy(x) in the Torch7? [duplicate]
问题 This question already exists : what is mean by implement color_content_masks = deepcopy(color_content_masks) in the Torch7 code below? Closed 2 years ago . if is_pooling then for k = 1, #color_codes do color_content_masks[k] = image.scale(color_content_masks[k], math.ceil(color_content_masks[k]:size(2)/2), math.ceil(color_content_masks[k]:size(1)/2)) color_style_masks[k] = image.scale(color_style_masks[k], math.ceil(color_style_masks[k]:size(2)/2), math.ceil(color_style_masks[k]:size(1)/2))