What is the benifit of using --quad option?

[imyhxy]

Hi there, I have noticed that there is a --quad option in the train.py script which will collect 4 normal images into single big one in the collate step of the dataloader process. And I have trained w/wo this option and observed no significant difference on my custom dataset. Can you explain when should we use --quad to get a better result?

[glenn-jocher]

@imyhxy it's an experiment that allows for occasional usage of 2x larger images without requiring the extra GPU memory. It goes with collate_fcn4():

yolov5/utils/datasets.py

Lines 594 to 619 in b7e985e

	@staticmethod
	def collate_fn4(batch):
	img, label, path, shapes = zip(*batch) # transposed
	n = len(shapes) // 4
	img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
	ho = torch.tensor([[0., 0, 0, 1, 0, 0]])
	wo = torch.tensor([[0., 0, 1, 0, 0, 0]])
	s = torch.tensor([[1, 1, .5, .5, .5, .5]]) # scale
	for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW
	i *= 4
	if random.random() < 0.5:
	im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[
	0].type(img[i].type())
	l = label[i]
	else:
	im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
	l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
	img4.append(im)
	label4.append(l)
	for i, l in enumerate(label4):
	l[:, 0] = i # add target image index for build_targets()
	return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4