返回 JoyAI-Echo
spatial_rational_resampler.py
根目录 / ltx-core / src / ltx_core / model / upsampler / spatial_rational_resampler.py
1 from typing import Tuple
2
3 import torch
4 from einops import rearrange
5
6 from ltx_core.model.upsampler.blur_downsample import BlurDownsample
7 from ltx_core.model.upsampler.pixel_shuffle import PixelShuffleND
8
9
10 def _rational_for_scale(scale: float) -> Tuple[int, int]:
11 mapping = {0.75: (3, 4), 1.5: (3, 2), 2.0: (2, 1), 4.0: (4, 1)}
12 if float(scale) not in mapping:
13 raise ValueError(f"Unsupported scale {scale}. Choose from {list(mapping.keys())}")
14 return mapping[float(scale)]
15
16
17 class SpatialRationalResampler(torch.nn.Module):
18 """
19 Fully-learned rational spatial scaling: up by 'num' via PixelShuffle, then anti-aliased
20 downsample by 'den' using fixed blur + stride. Operates on H,W only.
21 For dims==3, work per-frame for spatial scaling (temporal axis untouched).
22 Args:
23 mid_channels (`int`): Number of intermediate channels for the convolution layer
24 scale (`float`): Spatial scaling factor. Supported values are:
25 - 0.75: Downsample by 3/4 (reduce spatial size)
26 - 1.5: Upsample by 3/2 (increase spatial size)
27 - 2.0: Upsample by 2x (double spatial size)
28 - 4.0: Upsample by 4x (quadruple spatial size)
29 Any other value will raise a ValueError.
30 """
31
32 def __init__(self, mid_channels: int, scale: float):
33 super().__init__()
34 self.scale = float(scale)
35 self.num, self.den = _rational_for_scale(self.scale)
36 self.conv = torch.nn.Conv2d(mid_channels, (self.num**2) * mid_channels, kernel_size=3, padding=1)
37 self.pixel_shuffle = PixelShuffleND(2, upscale_factors=(self.num, self.num))
38 self.blur_down = BlurDownsample(dims=2, stride=self.den)
39
40 def forward(self, x: torch.Tensor) -> torch.Tensor:
41 b, _, f, _, _ = x.shape
42 x = rearrange(x, "b c f h w -> (b f) c h w")
43 x = self.conv(x)
44 x = self.pixel_shuffle(x)
45 x = self.blur_down(x)
46 x = rearrange(x, "(b f) c h w -> b c f h w", b=b, f=f)
47 return x
48
48 lines PYTHON