Spaces:
Running
Running
File size: 8,301 Bytes
99e2b6c |
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 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 |
import torch
import torch.nn as nn
import torch.nn.functional as F
import warnings
warnings.filterwarnings("ignore")
import torchvision
import sys
import os
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
import depth_only_parameters as params
def getConvLayer(in_channel, out_channel, stride=1, padding=1, activation=nn.ReLU()):
return nn.Sequential(
nn.Conv2d(in_channel, out_channel,
kernel_size=3,
stride=stride,
padding=padding,
padding_mode='reflect'),
activation
)
def getConvTransposeLayer(in_channel, out_channel, kernel=3, stride=1, padding=1, activation=nn.ReLU()):
return nn.Sequential(
nn.ConvTranspose2d(in_channel,
out_channel,
kernel_size=kernel,
stride=stride,
padding=padding),
activation
)
class Flatten(nn.Module):
def forward(self, input):
return input.view(input.size(0), -1)
class UnFlatten(nn.Module):
def forward(self, input, size=1):
return input.view(input.size(0), 1, params.params_height//8, params.params_width//8)
class ResidualBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride=1):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3,
stride=stride, padding=1, bias=False)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3,
stride=1, padding=1, bias=False)
self.stride = stride
self.shortcut = nn.Sequential()
if stride != 1 or in_channels != out_channels:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=1,
stride=stride, bias=False),
nn.BatchNorm2d(out_channels)
)
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.relu(out)
out = self.conv2(out)
out = out + self.shortcut(residual)
out = self.relu(out)
return out
class UpperEncoder(nn.Module):
def __init__(self):
super().__init__()
model = torchvision.models.resnet152(pretrained=True)
layers = list(model.children())
self.ResNetEncoder = nn.Sequential(*layers[:5].copy())
del model
def forward(self, x):
x1 = x[:, 0:3, :, :]
x1 = self.ResNetEncoder(x1)
return x1
def apply_resnet_encoder(self, x):
x1 = x[:, 0:3, :, :]
x1 = self.ResNetEncoder(x1)
return x1
class LowerEncoder(nn.Module):
def __init__(self, total_image_input=1):
super().__init__()
# Halved channels compared to the original
self.encoder_pre = ResidualBlock(total_image_input*3, 10)
self.encoder_layer1 = ResidualBlock(10, 15)
self.encoder_layer2 = ResidualBlock(15, 25)
self.encoder_layer3 = nn.Sequential(
ResidualBlock(25, 50),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.encoder_layer4 = ResidualBlock(50, 100)
self.encoder_layer5 = nn.Sequential(
ResidualBlock(100, 200),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.encoder_layer6 = ResidualBlock(200, 300)
self.encoder_layer7 = nn.Sequential(
ResidualBlock(300, 400),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.encoder_layer8 = ResidualBlock(400, 500)
self.encoder_layer9 = nn.Sequential(
ResidualBlock(500, 600),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.encoder_layer10 = ResidualBlock(600, 700)
self.encoder_layer11 = ResidualBlock(700, 800)
def forward(self, x):
x = self.encoder_pre(x)
x = self.encoder_layer1(x)
x = self.encoder_layer2(x)
skip1 = self.encoder_layer3(x)
x = self.encoder_layer4(skip1)
skip2 = self.encoder_layer5(x)
x = self.encoder_layer6(skip2)
skip3 = self.encoder_layer7(x)
x = self.encoder_layer8(skip3)
skip4 = self.encoder_layer9(x)
x = self.encoder_layer10(skip4)
x = self.encoder_layer11(x)
return x, [skip1, skip2, skip3, skip4]
class MergeDecoder(nn.Module):
def __init__(self):
super().__init__()
# Halved channels for decoder blocks
self.decoder_layer1 = ResidualBlock(800, 700)
self.decoder_layer2 = ResidualBlock(700, 600)
self.decoder_layer3 = ResidualBlock(600, 500)
self.decoder_layer4 = nn.Sequential(
nn.ConvTranspose2d(500, 400, kernel_size=2, stride=2, padding=0),
nn.ReLU(True)
)
self.decoder_layer5 = ResidualBlock(400, 300)
self.decoder_layer6 = nn.Sequential(
nn.ConvTranspose2d(300, 200, kernel_size=2, stride=2, padding=0),
nn.ReLU(True)
)
self.decoder_layer7 = ResidualBlock(200, 100)
self.decoder_layer8 = nn.Sequential(
nn.ConvTranspose2d(100, 50, kernel_size=2, stride=2, padding=0),
nn.ReLU(True)
)
self.decoder_layer9 = ResidualBlock(50, 50)
self.decoder_layer10 = nn.Sequential(
nn.ConvTranspose2d(50, 50, kernel_size=2, stride=2, padding=0),
nn.ReLU(True)
)
self.decoder_layer11 = ResidualBlock(50, 50)
self.decoder_layer12 = ResidualBlock(50, 25)
self.decoder_layer13 = ResidualBlock(25, 20)
self.decoder_layer14 = ResidualBlock(20, 10)
self.decoder_layer15 = nn.Sequential(
nn.Conv2d(10, 4, kernel_size=3, stride=1, padding=1),
nn.ReLU(True)
)
self.decoder_layer16 = nn.Sequential(
nn.Conv2d(4, 1, kernel_size=3, stride=1, padding=1),
nn.ReLU(True)
)
def forward(self, x, lower_skip_list, upper_skip_list):
x = self.decoder_layer1(x)
x = self.decoder_layer2(x)
# Expecting lower_skip_list[3] and upper_skip_list[1] to have matching dimensions
x = x + lower_skip_list[3] + upper_skip_list[1]
x = self.decoder_layer3(x)
x = self.decoder_layer4(x)
x = x + lower_skip_list[2] + upper_skip_list[0]
x = self.decoder_layer5(x)
x = self.decoder_layer6(x)
x = x + lower_skip_list[1]
x = self.decoder_layer7(x)
x = self.decoder_layer8(x)
x = x + lower_skip_list[0]
x = self.decoder_layer9(x)
x = self.decoder_layer10(x)
x = self.decoder_layer11(x)
x = self.decoder_layer12(x)
x = self.decoder_layer13(x)
x = self.decoder_layer14(x)
x = self.decoder_layer15(x)
x = self.decoder_layer16(x)
return x
class PVSDNet_Lite(nn.Module):
def __init__(self, total_image_input=1):
super().__init__()
# Upper encoder remains mostly the same
self.upper_encoder = UpperEncoder()
self.lower_encoder = LowerEncoder(total_image_input)
self.merge_decoder = MergeDecoder()
# Halved extra layers for upper branch:
self.upper_encoder_extra_1 = nn.Sequential(
ResidualBlock(256, 400),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.upper_encoder_extra_2 = nn.Sequential(
ResidualBlock(400, 600),
nn.MaxPool2d(kernel_size=2, stride=2)
)
def forward(self, x):
# First Encoder Branch (Upper)
upper_features_1 = self.upper_encoder.apply_resnet_encoder(x)
upper_features_1 = self.upper_encoder_extra_1(upper_features_1)
upper_features_2 = self.upper_encoder_extra_2(upper_features_1)
# Second Encoder Branch (Lower)
lower_feature, skip_list = self.lower_encoder(x)
# Merge and decode features
merged_feature = self.merge_decoder(lower_feature, skip_list, [upper_features_1, upper_features_2])
return merged_feature
|