File size: 3,972 Bytes
b9425fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
import imp
import torch
import torch.nn as nn
import torch.nn.functional as F
from timm.models.layers import DropPath
class UpSampleConvnext(nn.Module):
def __init__(self, ratio, inchannel, outchannel):
super().__init__()
self.ratio = ratio
self.channel_reschedule = nn.Sequential(
# LayerNorm(inchannel, eps=1e-6, data_format="channels_last"),
nn.Linear(inchannel, outchannel),
LayerNorm(outchannel, eps=1e-6, data_format="channels_last"))
self.upsample = nn.Upsample(scale_factor=2**ratio, mode='nearest')
def forward(self, x):
x = x.permute(0, 2, 3, 1)
x = self.channel_reschedule(x)
x = x = x.permute(0, 3, 1, 2)
return self.upsample(x)
class LayerNorm(nn.Module):
r""" LayerNorm that supports two data formats: channels_last (default) or channels_first.
The ordering of the dimensions in the inputs. channels_last corresponds to inputs with
shape (batch_size, height, width, channels) while channels_first corresponds to inputs
with shape (batch_size, channels, height, width).
"""
def __init__(self, normalized_shape, eps=1e-6, data_format="channels_first"):
super().__init__()
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.bias = nn.Parameter(torch.zeros(normalized_shape))
self.eps = eps
self.data_format = data_format
if self.data_format not in ["channels_last", "channels_first"]:
raise NotImplementedError
self.normalized_shape = (normalized_shape, )
def forward(self, x):
if self.data_format == "channels_last":
return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
elif self.data_format == "channels_first":
u = x.mean(1, keepdim=True)
s = (x - u).pow(2).mean(1, keepdim=True)
x = (x - u) / torch.sqrt(s + self.eps)
x = self.weight[:, None, None] * x + self.bias[:, None, None]
return x
class ConvNextBlock(nn.Module):
r""" ConvNeXt Block. There are two equivalent implementations:
(1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)
(2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back
We use (2) as we find it slightly faster in PyTorch
Args:
dim (int): Number of input channels.
drop_path (float): Stochastic depth rate. Default: 0.0
layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
"""
def __init__(self, in_channel, hidden_dim, out_channel, kernel_size=3, layer_scale_init_value=1e-6, drop_path= 0.0):
super().__init__()
self.dwconv = nn.Conv2d(in_channel, in_channel, kernel_size=kernel_size, padding=(kernel_size - 1) // 2, groups=in_channel) # depthwise conv
self.norm = nn.LayerNorm(in_channel, eps=1e-6)
self.pwconv1 = nn.Linear(in_channel, hidden_dim) # pointwise/1x1 convs, implemented with linear layers
self.act = nn.GELU()
self.pwconv2 = nn.Linear(hidden_dim, out_channel)
self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((out_channel)),
requires_grad=True) if layer_scale_init_value > 0 else None
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
def forward(self, x):
input = x
x = self.dwconv(x)
x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
x = self.norm(x)
x = self.pwconv1(x)
x = self.act(x)
x = self.pwconv2(x)
if self.gamma is not None:
x = self.gamma * x
x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)
x = input + self.drop_path(x)
return x |