105 lines
3.5 KiB
Python
105 lines
3.5 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
from collections import OrderedDict
|
|
from videocrafter.lvdm.models.modules.util import (
|
|
zero_module,
|
|
conv_nd,
|
|
avg_pool_nd
|
|
)
|
|
|
|
class Downsample(nn.Module):
|
|
"""
|
|
A downsampling layer with an optional convolution.
|
|
:param channels: channels in the inputs and outputs.
|
|
:param use_conv: a bool determining if a convolution is applied.
|
|
:param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
|
|
downsampling occurs in the inner-two dimensions.
|
|
"""
|
|
|
|
def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
|
|
super().__init__()
|
|
self.channels = channels
|
|
self.out_channels = out_channels or channels
|
|
self.use_conv = use_conv
|
|
self.dims = dims
|
|
stride = 2 if dims != 3 else (1, 2, 2)
|
|
if use_conv:
|
|
self.op = conv_nd(
|
|
dims, self.channels, self.out_channels, 3, stride=stride, padding=padding
|
|
)
|
|
else:
|
|
assert self.channels == self.out_channels
|
|
self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)
|
|
|
|
def forward(self, x):
|
|
assert x.shape[1] == self.channels
|
|
return self.op(x)
|
|
|
|
|
|
class ResnetBlock(nn.Module):
|
|
def __init__(self, in_c, out_c, down, ksize=3, sk=False, use_conv=True):
|
|
super().__init__()
|
|
ps = ksize // 2
|
|
if in_c != out_c or sk == False:
|
|
self.in_conv = nn.Conv2d(in_c, out_c, ksize, 1, ps)
|
|
else:
|
|
# print('n_in')
|
|
self.in_conv = None
|
|
self.block1 = nn.Conv2d(out_c, out_c, 3, 1, 1)
|
|
self.act = nn.ReLU()
|
|
self.block2 = nn.Conv2d(out_c, out_c, ksize, 1, ps)
|
|
if sk == False:
|
|
self.skep = nn.Conv2d(in_c, out_c, ksize, 1, ps)
|
|
else:
|
|
self.skep = None
|
|
|
|
self.down = down
|
|
if self.down == True:
|
|
self.down_opt = Downsample(in_c, use_conv=use_conv)
|
|
|
|
def forward(self, x):
|
|
if self.down == True:
|
|
x = self.down_opt(x)
|
|
if self.in_conv is not None: # edit
|
|
x = self.in_conv(x)
|
|
|
|
h = self.block1(x)
|
|
h = self.act(h)
|
|
h = self.block2(h)
|
|
if self.skep is not None:
|
|
return h + self.skep(x)
|
|
else:
|
|
return h + x
|
|
|
|
|
|
class Adapter(nn.Module):
|
|
def __init__(self, channels=[320, 640, 1280, 1280], nums_rb=3, cin=64, ksize=3, sk=False, use_conv=True):
|
|
super(Adapter, self).__init__()
|
|
self.unshuffle = nn.PixelUnshuffle(8)
|
|
self.channels = channels
|
|
self.nums_rb = nums_rb
|
|
self.body = []
|
|
for i in range(len(channels)):
|
|
for j in range(nums_rb):
|
|
if (i != 0) and (j == 0):
|
|
self.body.append(
|
|
ResnetBlock(channels[i - 1], channels[i], down=True, ksize=ksize, sk=sk, use_conv=use_conv))
|
|
else:
|
|
self.body.append(
|
|
ResnetBlock(channels[i], channels[i], down=False, ksize=ksize, sk=sk, use_conv=use_conv))
|
|
self.body = nn.ModuleList(self.body)
|
|
self.conv_in = nn.Conv2d(cin, channels[0], 3, 1, 1)
|
|
|
|
def forward(self, x):
|
|
# unshuffle
|
|
x = self.unshuffle(x)
|
|
# extract features
|
|
features = []
|
|
x = self.conv_in(x)
|
|
for i in range(len(self.channels)):
|
|
for j in range(self.nums_rb):
|
|
idx = i * self.nums_rb + j
|
|
x = self.body[idx](x)
|
|
features.append(x)
|
|
|
|
return features |