def downsample2d(x,
f,
down=2,
padding=0,
flip_filter=False,
gain=1,
impl='cuda'):
r"""Downsample a batch of 2D images using the given 2D FIR filter.
By default, the result is padded so that its shape is a fraction of the
input.
User-specified padding is applied on top of that, with negative values
indicating cropping. Pixels outside the image are assumed to be zero.
Args:
x: Float32/float64/float16 input tensor of the shape
`[batch_size, num_channels, in_height, in_width]`.
f: Float32 FIR filter of the shape
`[filter_height, filter_width]` (non-separable),
`[filter_taps]` (separable), or
`None` (identity).
down: Integer downsampling factor. Can be a single int or a
list/tuple
`[x, y]` (default: 1).
padding: Padding with respect to the input. Can be a single number
or a
list/tuple `[x, y]` or `[x_before, x_after, y_before,
y_after]`
(default: 0).
flip_filter: False = convolution, True = correlation (default: False).
gain: Overall scaling factor for signal magnitude (default: 1).
impl: Implementation to use. Can be `'ref'` or `'cuda'`
(default: `'cuda'`).
Returns:
Tensor of the shape `[batch_size, num_channels, out_height, out_width]`
"""
downx, downy = _parse_scaling(down)
padx0, padx1, pady0, pady1 = _parse_padding(padding)
fw, fh = _get_filter_size(f)
p = [
padx0 + (fw - downx + 1) // 2,
padx1 + (fw - downx) // 2,
pady0 + (fh - downy + 1) // 2,
pady1 + (fh - downy) // 2,
]
if flip_filter:
f = f.flip(list(range(f.ndim)))
if f.ndim == 1:
x = upfirdn2d(
x, f.unsqueeze(0), down=(downx, 1), pad=(p[0], p[1], 0, 0))
x = upfirdn2d(
x, f.unsqueeze(1), down=(1, downy), pad=(0, 0, p[2], p[3]))
return x
def forward(self, input):
out = upfirdn2d(input,
self.kernel,
up=1,
down=self.factor,
pad=self.pad)
return out
def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input feature map with shape of (N, C, H, W).
Returns:
Tensor: Output feature map.
"""
return upfirdn2d(x, self.kernel, pad=self.pad)
def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input feature map with shape of (N, C, H, W).
Returns:
Tensor: Output feature map.
"""
out = upfirdn2d(x, self.kernel, up=self.factor, down=1, pad=self.pad)
return out
def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input feature map with shape of (N, C, H, W).
Returns:
Tensor: Output feature map.
"""
# In Tero's implementation, he uses fp32
return upfirdn2d(x, self.kernel.to(x.dtype), pad=self.pad)
def forward(self, input):
"""Forward function.
Args:
input (Tensor): Input feature map with shape of (N, C, H, W).
Returns:
Tensor: Output feature map.
"""
out = upfirdn2d(input,
self.kernel.to(input.dtype),
up=1,
down=self.factor,
pad=self.pad)
return out
def forward(self, x):
return upfirdn2d(x, self.kernel, pad=self.pad)
def forward(self, x):
out = upfirdn2d(x, self.kernel, up=self.factor, down=1, pad=self.pad)
return out
