def __init__(self,
img_size=224,
patch_size=16,
in_chans=3,
in_dim=48,
stride=4):
super().__init__()
img_size = to_2tuple(img_size)
patch_size = to_2tuple(patch_size)
# grid_size property necessary for resizing positional embedding
self.grid_size = (img_size[0] // patch_size[0],
img_size[1] // patch_size[1])
num_patches = (self.grid_size[0]) * (self.grid_size[1])
self.img_size = img_size
self.num_patches = num_patches
self.in_dim = in_dim
new_patch_size = [math.ceil(ps / stride) for ps in patch_size]
self.new_patch_size = new_patch_size
self.proj = nn.Conv2d(in_chans,
self.in_dim,
kernel_size=7,
padding=3,
stride=stride)
self.unfold = nn.Unfold(kernel_size=new_patch_size,
stride=new_patch_size)
def __init__(self,
patch_size=16,
stride=16,
padding=0,
in_chans=3,
embed_dim=768,
norm_layer=None):
super().__init__()
patch_size = to_2tuple(patch_size)
stride = to_2tuple(stride)
padding = to_2tuple(padding)
self.proj = nn.Conv2d(in_chans,
embed_dim,
kernel_size=patch_size,
stride=stride,
padding=padding)
self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768, norm_layer=None,exist_overlap:bool=False,slide_step=None):
super().__init__()
img_size = to_2tuple(img_size)
patch_size = to_2tuple(patch_size)
self.img_size = img_size
if exist_overlap:
self.num_patches = ((img_size[0] - patch_size[0]) // slide_step + 1) * ((img_size[1] - patch_size[1]) // slide_step + 1)
self.proj = nn.Conv2d(in_channels=in_chans,
out_channels=embed_dim,
kernel_size=patch_size,
stride=(slide_step, slide_step))
else:
self.patch_size = patch_size
self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
self.num_patches = self.grid_size[0] * self.grid_size[1]
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)
self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
