212 lines
7.3 KiB
Python
212 lines
7.3 KiB
Python
|
import torch
|
||
|
|
import torch.nn as nn
|
||
|
|
import torch.nn.functional as F
|
||
|
|
import timm
|
||
|
|
import math
|
||
|
|
from .submodule import *
|
||
|
|
|
||
|
|
class ResidualBlock(nn.Module):
|
||
|
|
def __init__(self, in_planes, planes, norm_fn='group', stride=1):
|
||
|
|
super(ResidualBlock, self).__init__()
|
||
|
|
|
||
|
|
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, padding=1, stride=stride)
|
||
|
|
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1)
|
||
|
|
self.relu = nn.ReLU(inplace=True)
|
||
|
|
|
||
|
|
num_groups = planes // 8
|
||
|
|
|
||
|
|
if norm_fn == 'group':
|
||
|
|
self.norm1 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
|
||
|
|
self.norm2 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
|
||
|
|
if not (stride == 1 and in_planes == planes):
|
||
|
|
self.norm3 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
|
||
|
|
|
||
|
|
elif norm_fn == 'batch':
|
||
|
|
self.norm1 = nn.BatchNorm2d(planes)
|
||
|
|
self.norm2 = nn.BatchNorm2d(planes)
|
||
|
|
if not (stride == 1 and in_planes == planes):
|
||
|
|
self.norm3 = nn.BatchNorm2d(planes)
|
||
|
|
|
||
|
|
elif norm_fn == 'instance':
|
||
|
|
self.norm1 = nn.InstanceNorm2d(planes)
|
||
|
|
self.norm2 = nn.InstanceNorm2d(planes)
|
||
|
|
if not (stride == 1 and in_planes == planes):
|
||
|
|
self.norm3 = nn.InstanceNorm2d(planes)
|
||
|
|
|
||
|
|
elif norm_fn == 'none':
|
||
|
|
self.norm1 = nn.Sequential()
|
||
|
|
self.norm2 = nn.Sequential()
|
||
|
|
if not (stride == 1 and in_planes == planes):
|
||
|
|
self.norm3 = nn.Sequential()
|
||
|
|
|
||
|
|
if stride == 1 and in_planes == planes:
|
||
|
|
self.downsample = None
|
||
|
|
|
||
|
|
else:
|
||
|
|
self.downsample = nn.Sequential(
|
||
|
|
nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride), self.norm3)
|
||
|
|
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
y = x
|
||
|
|
y = self.conv1(y)
|
||
|
|
y = self.norm1(y)
|
||
|
|
y = self.relu(y)
|
||
|
|
y = self.conv2(y)
|
||
|
|
y = self.norm2(y)
|
||
|
|
y = self.relu(y)
|
||
|
|
|
||
|
|
if self.downsample is not None:
|
||
|
|
x = self.downsample(x)
|
||
|
|
|
||
|
|
return self.relu(x+y)
|
||
|
|
|
||
|
|
class MultiBasicEncoder(nn.Module):
|
||
|
|
def __init__(self, output_dim=[128], norm_fn='batch', dropout=0.0, downsample=3):
|
||
|
|
super(MultiBasicEncoder, self).__init__()
|
||
|
|
self.norm_fn = norm_fn
|
||
|
|
self.downsample = downsample
|
||
|
|
|
||
|
|
if self.norm_fn == 'group':
|
||
|
|
self.norm1 = nn.GroupNorm(num_groups=8, num_channels=64)
|
||
|
|
|
||
|
|
elif self.norm_fn == 'batch':
|
||
|
|
self.norm1 = nn.BatchNorm2d(64)
|
||
|
|
|
||
|
|
elif self.norm_fn == 'instance':
|
||
|
|
self.norm1 = nn.InstanceNorm2d(64)
|
||
|
|
|
||
|
|
elif self.norm_fn == 'none':
|
||
|
|
self.norm1 = nn.Sequential()
|
||
|
|
|
||
|
|
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=1 + (downsample > 2), padding=3)
|
||
|
|
self.relu1 = nn.ReLU(inplace=True)
|
||
|
|
|
||
|
|
self.in_planes = 64
|
||
|
|
self.layer1 = self._make_layer(64, stride=1)
|
||
|
|
self.layer2 = self._make_layer(96, stride=1 + (downsample > 1))
|
||
|
|
self.layer3 = self._make_layer(128, stride=1 + (downsample > 0))
|
||
|
|
self.layer4 = self._make_layer(128, stride=2)
|
||
|
|
self.layer5 = self._make_layer(128, stride=2)
|
||
|
|
|
||
|
|
output_list = []
|
||
|
|
|
||
|
|
for dim in output_dim:
|
||
|
|
conv_out = nn.Sequential(
|
||
|
|
ResidualBlock(128, 128, self.norm_fn, stride=1),
|
||
|
|
nn.Conv2d(128, dim[2], 3, padding=1))
|
||
|
|
output_list.append(conv_out)
|
||
|
|
|
||
|
|
self.outputs04 = nn.ModuleList(output_list)
|
||
|
|
|
||
|
|
output_list = []
|
||
|
|
for dim in output_dim:
|
||
|
|
conv_out = nn.Sequential(
|
||
|
|
ResidualBlock(128, 128, self.norm_fn, stride=1),
|
||
|
|
nn.Conv2d(128, dim[1], 3, padding=1))
|
||
|
|
output_list.append(conv_out)
|
||
|
|
|
||
|
|
self.outputs08 = nn.ModuleList(output_list)
|
||
|
|
|
||
|
|
output_list = []
|
||
|
|
for dim in output_dim:
|
||
|
|
conv_out = nn.Conv2d(128, dim[0], 3, padding=1)
|
||
|
|
output_list.append(conv_out)
|
||
|
|
|
||
|
|
self.outputs16 = nn.ModuleList(output_list)
|
||
|
|
|
||
|
|
if dropout > 0:
|
||
|
|
self.dropout = nn.Dropout2d(p=dropout)
|
||
|
|
else:
|
||
|
|
self.dropout = None
|
||
|
|
|
||
|
|
for m in self.modules():
|
||
|
|
if isinstance(m, nn.Conv2d):
|
||
|
|
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||
|
|
elif isinstance(m, (nn.BatchNorm2d, nn.InstanceNorm2d, nn.GroupNorm)):
|
||
|
|
if m.weight is not None:
|
||
|
|
nn.init.constant_(m.weight, 1)
|
||
|
|
if m.bias is not None:
|
||
|
|
nn.init.constant_(m.bias, 0)
|
||
|
|
|
||
|
|
def _make_layer(self, dim, stride=1):
|
||
|
|
layer1 = ResidualBlock(self.in_planes, dim, self.norm_fn, stride=stride)
|
||
|
|
layer2 = ResidualBlock(dim, dim, self.norm_fn, stride=1)
|
||
|
|
layers = (layer1, layer2)
|
||
|
|
|
||
|
|
self.in_planes = dim
|
||
|
|
return nn.Sequential(*layers)
|
||
|
|
|
||
|
|
def forward(self, x, dual_inp=False, num_layers=3):
|
||
|
|
|
||
|
|
x = self.conv1(x)
|
||
|
|
x = self.norm1(x)
|
||
|
|
x = self.relu1(x)
|
||
|
|
|
||
|
|
x = self.layer1(x)
|
||
|
|
x = self.layer2(x)
|
||
|
|
x = self.layer3(x)
|
||
|
|
|
||
|
|
if dual_inp:
|
||
|
|
v = x
|
||
|
|
x = x[:(x.shape[0]//2)]
|
||
|
|
|
||
|
|
outputs04 = [f(x) for f in self.outputs04]
|
||
|
|
if num_layers == 1:
|
||
|
|
return (outputs04, v) if dual_inp else (outputs04,)
|
||
|
|
|
||
|
|
y = self.layer4(x)
|
||
|
|
outputs08 = [f(y) for f in self.outputs08]
|
||
|
|
|
||
|
|
if num_layers == 2:
|
||
|
|
return (outputs04, outputs08, v) if dual_inp else (outputs04, outputs08)
|
||
|
|
|
||
|
|
z = self.layer5(y)
|
||
|
|
outputs16 = [f(z) for f in self.outputs16]
|
||
|
|
|
||
|
|
return (outputs04, outputs08, outputs16, v) if dual_inp else (outputs04, outputs08, outputs16)
|
||
|
|
|
||
|
|
class Feature(SubModule):
|
||
|
|
def __init__(self):
|
||
|
|
super(Feature, self).__init__()
|
||
|
|
pretrained = True
|
||
|
|
model = timm.create_model('mobilenetv2_100', pretrained=pretrained, features_only=True)
|
||
|
|
|
||
|
|
layers = [1,2,3,5,6]
|
||
|
|
chans = [16, 24, 32, 96, 160]
|
||
|
|
self.conv_stem = model.conv_stem
|
||
|
|
self.bn1 = model.bn1
|
||
|
|
|
||
|
|
self.block0 = torch.nn.Sequential(*model.blocks[0:layers[0]])
|
||
|
|
self.block1 = torch.nn.Sequential(*model.blocks[layers[0]:layers[1]])
|
||
|
|
self.block2 = torch.nn.Sequential(*model.blocks[layers[1]:layers[2]])
|
||
|
|
self.block3 = torch.nn.Sequential(*model.blocks[layers[2]:layers[3]])
|
||
|
|
self.block4 = torch.nn.Sequential(*model.blocks[layers[3]:layers[4]])
|
||
|
|
|
||
|
|
self.deconv32_16 = Conv2x_IN(chans[4], chans[3], deconv=True, concat=True)
|
||
|
|
self.deconv16_8 = Conv2x_IN(chans[3]*2, chans[2], deconv=True, concat=True)
|
||
|
|
self.deconv8_4 = Conv2x_IN(chans[2]*2, chans[1], deconv=True, concat=True)
|
||
|
|
self.conv4 = BasicConv_IN(chans[1]*2, chans[1]*2, kernel_size=3, stride=1, padding=1)
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
B, V, _, H, W = x.size()
|
||
|
|
x = x.view(B * V, -1, H, W)
|
||
|
|
#x = self.act1(self.bn1(self.conv_stem(x)))
|
||
|
|
x = self.bn1(self.conv_stem(x))
|
||
|
|
x2 = self.block0(x)
|
||
|
|
x4 = self.block1(x2)
|
||
|
|
# return x4,x4,x4,x4
|
||
|
|
x8 = self.block2(x4)
|
||
|
|
x16 = self.block3(x8)
|
||
|
|
x32 = self.block4(x16)
|
||
|
|
|
||
|
|
x16 = self.deconv32_16(x32, x16)
|
||
|
|
x8 = self.deconv16_8(x16, x8)
|
||
|
|
x4 = self.deconv8_4(x8, x4)
|
||
|
|
x4 = self.conv4(x4)
|
||
|
|
|
||
|
|
x4 = x4.view(B, V, -1, H // 4, W // 4)
|
||
|
|
x8 = x8.view(B, V, -1, H // 8, W // 8)
|
||
|
|
x16 = x16.view(B, V, -1, H // 16, W // 16)
|
||
|
|
x32 = x32.view(B, V, -1, H // 32, W // 32)
|
||
|
|
return [x4, x8, x16, x32]
|