File size: 6,403 Bytes
f3972ea |
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 |
import torch
import torch.nn as nn
import torch.nn.functional as F
class ResidualBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride = 1, downsample = None):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size = 3, stride = stride, padding = 1),
nn.BatchNorm2d(out_channels),
nn.ReLU())
self.conv2 = nn.Sequential(
nn.Conv2d(out_channels, out_channels, kernel_size = 3, stride = 1, padding = 1),
nn.BatchNorm2d(out_channels))
self.downsample = downsample
self.relu = nn.ReLU()
self.out_channels = out_channels
self.dropout_percentage = 0.5
self.dropout1 = nn.Dropout(p=self.dropout_percentage)
self.batchnorm_mod = nn.BatchNorm2d(out_channels)
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.dropout1(out)
# out = self.batchnorm_mod(out)
out = self.conv2(out)
out = self.dropout1(out)
# out = self.batchnorm_mod(out)
if self.downsample:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, inchan, block, layers, num_classes = 10):
super(ResNet, self).__init__()
self.inplanes = 64
self.eps = 1e-5
self.relu = nn.ReLU()
self.conv1 = nn.Sequential(
nn.Conv2d(inchan, 64, kernel_size = 7, stride = 2, padding = 3),
nn.BatchNorm2d(64),
nn.ReLU())
self.maxpool = nn.MaxPool2d(kernel_size = (2, 2), stride = 2, padding = 1)
self.layer0 = self._make_layer(block, 64, layers[0], stride = 1)
self.layer1 = self._make_layer(block, 128, layers[1], stride = 2)
self.layer2 = self._make_layer(block, 256, layers[2], stride = 2)
self.layer3 = self._make_layer(block, 512, layers[3], stride = 1)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(39424, num_classes)
self.dropout_percentage = 0.3
self.dropout1 = nn.Dropout(p=self.dropout_percentage)
# Encoder
self.encoder = nn.Sequential(
nn.Conv2d(24, 32, kernel_size = 3, stride =1, padding = 1),
nn.ReLU(True),nn.Dropout(p=self.dropout_percentage),
nn.Conv2d(32, 64, kernel_size = 3, stride =1, padding = 1),
nn.ReLU(True),nn.Dropout(p=self.dropout_percentage),
nn.Conv2d(64, 32, kernel_size = 3, stride = 1, padding = 1),
nn.ReLU(True),nn.Dropout(p=self.dropout_percentage),
nn.Conv2d(32, 24, kernel_size = 3, stride = 1, padding = 1),
nn.Sigmoid()
)
params = sum(p.numel() for p in self.encoder.parameters())
print("num params encoder ",params)
def norm(self, x):
shifted = x-x.min()
maxes = torch.amax(abs(shifted), dim=(-2, -1))
repeated_maxes = maxes.unsqueeze(2).unsqueeze(3).repeat(1, 1, x.shape[-2],x.shape[-1])
x = shifted/repeated_maxes
return x
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes, kernel_size=1, stride=stride),
nn.BatchNorm2d(planes),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x, return_mask=False):
# # m = self.encoder(x).unsqueeze(-1).repeat(1, 1, 1, x.shape[-1])
m = self.encoder(x)
self.mask = m
self.value = x
# # m = nn.Sigmoid()(self.encoder(x))
x = x * m
# x = self.norm(x)
x = self.conv1(x)
x = self.maxpool(x)
x = self.layer0(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.dropout1(x)
x = self.fc(x)
return x
# if return_mask:
# return x, self.mask, self.value
# else:
# return x
class ConvAutoencoder(nn.Module):
def __init__(self):
super(ConvAutoencoder, self).__init__()
# Encoder
self.encoder = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=3, stride=2, padding=1), # (16, 96, 128)
nn.ReLU(),
nn.Conv2d(16, 32, kernel_size=3, stride=2, padding=1), # (32, 48, 64)
nn.ReLU(),
nn.Conv2d(32, 64, kernel_size=3, stride=2, padding=1), # (64, 24, 32)
nn.ReLU(),
nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),# (128, 12, 16)
nn.ReLU()
)
# Fully connected latent space
self.fc1 = nn.Linear(128 * 12 * 16, 8)
self.fc2 = nn.Linear(8, 128 * 12 * 16)
# Decoder
self.decoder = nn.Sequential(
nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, output_padding=1), # (64, 24, 32)
nn.ReLU(),
nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, output_padding=1), # (32, 48, 64)
nn.ReLU(),
nn.ConvTranspose2d(32, 16, kernel_size=3, stride=2, padding=1, output_padding=1), # (16, 96, 128)
nn.ReLU(),
nn.ConvTranspose2d(16, 3, kernel_size=3, stride=2, padding=1, output_padding=1), # (3, 192, 256)
nn.Sigmoid() # Using Sigmoid for the final activation to get output in range [0, 1]
)
def forward(self, x):
# Encode
x = self.encoder(x)
# Flatten the encoded output
x = x.view(x.size(0), -1)
# Fully connected latent space
x = self.fc1(x)
x = self.fc2(x)
# Reshape the output to the shape suitable for the decoder
x = x.view(x.size(0), 128, 12, 16)
# Decode
x = self.decoder(x)
return x
|