Why the patchembedding defaut img size is not equal to the image size in visualize attention?

[LWShowTime]

n visualize_attention.py:

dino/visualize_attention.py

Line 108 in 7c446df

parser.add_argument("--image_size", default=(480, 480), type=int, nargs="+", help="Resize image.")

However, in vision_transformer.py:

dino/vision_transformer.py

Lines 116 to 122 in 7c446df

	class PatchEmbed(nn.Module):
	""" Image to Patch Embedding
	"""
	def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768):
	super().__init__()
	num_patches = (img_size // patch_size) * (img_size // patch_size)
	self.img_size = img_size

Will this cause any performance drop?

[LWShowTime]

I notice in DINO, your team have delete this line from the origin ViT:
assert H == self.img_size[0], f"Input image height ({H}) doesn't match model ({self.img_size[0]}).

@piotr-bojanowski @mathildecaron31