mmagic.models.editors.stylegan2.ada.upfirdn2d¶
Module Contents¶
Functions¶
|
|
|
|
|
Upsample a batch of 2D images using the given 2D FIR filter. |
|
Convenience function to setup 2D FIR filter for upfirdn2d(). |
|
Downsample a batch of 2D images using the given 2D FIR filter. |
Attributes¶
- mmagic.models.editors.stylegan2.ada.upfirdn2d.upsample2d(x, f, up=2, padding=0, flip_filter=False, gain=1, impl='cuda')[source]¶
Upsample a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape is a multiple 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. :param x: Float32/float64/float16 input tensor of the shape
[batch_size, num_channels, in_height, in_width].
- Parameters
f – Float32 FIR filter of the shape [filter_height, filter_width] (non-separable), [filter_taps] (separable), or None (identity).
up – Integer upsampling factor. Can be a single int or a list/tuple [x, y] (default: 1).
padding – Padding with respect to the output. 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]
- mmagic.models.editors.stylegan2.ada.upfirdn2d.setup_filter(f, device=torch.device('cpu'), normalize=True, flip_filter=False, gain=1, separable=None)[source]¶
Convenience function to setup 2D FIR filter for upfirdn2d(). :param f: Torch tensor, numpy array, or python list of the shape
[filter_height, filter_width] (non-separable), [filter_taps] (separable), [] (impulse), or None (identity).
- Parameters
device – Result device (default: cpu).
normalize – Normalize the filter so that it retains the magnitude for constant input signal (DC)? (default: True).
flip_filter – Flip the filter? (default: False).
gain – Overall scaling factor for signal magnitude (default: 1).
separable – Return a separable filter? (default: select automatically)
- Returns
Float32 tensor of the shape [filter_height, filter_width] (non-separable) or [filter_taps] (separable).
- mmagic.models.editors.stylegan2.ada.upfirdn2d.downsample2d(x, f, down=2, padding=0, flip_filter=False, gain=1, impl='cuda')[source]¶
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. :param x: Float32/float64/float16 input tensor of the shape
[batch_size, num_channels, in_height, in_width].
- Parameters
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]