Spaces:
Sleeping
Sleeping
File size: 8,487 Bytes
65f6a85 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | #!/usr/bin/env python
# coding: utf-8
# In[1]:
import torch.nn as nn
import torchvision.transforms as transforms
# First Model
# In[ ]:
class PoseNetV1(nn.Module):
def __init__(self):
super(PoseNetV1, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 112x112
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 56x56
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 28x28
)
self.fc = nn.Sequential(
nn.Flatten(),
nn.Linear(512 * 14 * 14, 512),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(512, 32)
)
def forward(self, x):
x = self.conv(x)
x = self.fc(x)
return x
# Here, we added one more layer and we added Dropout to the fully connected layer. We also added a Flatten layer to flatten the output of the convolutional layers before passing it to the fully connected layers.
# In[ ]:
class PoseNetV2(nn.Module):
def __init__(self):
super(PoseNetV2, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 112x112
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 56x56
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 28x28
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 14x14
)
self.fc = nn.Sequential(
nn.Flatten(),
nn.Linear(256 * 14 * 14, 512),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(512, 32)
)
def forward(self, x):
x = self.conv(x)
x = self.fc(x)
return x
# In[ ]:
class PoseNetV3(nn.Module):
def __init__(self):
super(PoseNetV3, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 112x112
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 56x56
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 28x28
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 14x14
)
self.fc = nn.Sequential(
nn.Flatten(),
nn.Linear(256 * 14 * 14, 512),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(512, 32)
)
def forward(self, x):
x = self.conv(x)
x = self.fc(x)
return x
# We added batch normalization in each layer, Adaptive Pooling and a Tahn function at the end of the fully conected layers
# In[ ]:
class PoseNetV4(nn.Module):
def __init__(self):
super(PoseNetV4, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 112x112
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 56x56
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 28x28
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.AdaptiveAvgPool2d((7, 7)) # Adaptive pooling to make output size consistent
)
self.fc = nn.Sequential(
nn.Flatten(),
nn.Linear(256 * 7 * 7, 512),
nn.ReLU(),
nn.Dropout(0.4), # Increased dropout to prevent overfitting
nn.Linear(512, 32),
nn.Tanh() # Normalizing keypoint predictions
)
def forward(self, x):
x = self.conv(x)
x = self.fc(x)
return x
# 4 Layers -> 5 Layers
#
# Tahn() -> Sigmoid()
# In[ ]:
class PoseNetV5(nn.Module):
def __init__(self):
super(PoseNetV5, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 112x112
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 56x56
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 28x28
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.MaxPool2d(2, 2), # 28x28
nn.Conv2d(256, 512, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.AdaptiveAvgPool2d((7, 7)) # Adaptive pooling to make output size consistent
)
self.fc = nn.Sequential(
nn.Flatten(),
nn.Linear(512 * 7 * 7, 512),
nn.ReLU(),
nn.Dropout(0.50), # Increased dropout to prevent overfitting
nn.Linear(512, 32),
nn.Sigmoid() # Normalizing keypoint predictions
)
def forward(self, x):
x = self.conv(x)
x = self.fc(x)
return x
# In[ ]:
class ResidualBlock(nn.Module):
def __init__(self, in_channels, out_channels):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1)
self.bn1 = nn.BatchNorm2d(out_channels)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1)
self.bn2 = nn.BatchNorm2d(out_channels)
# Skip connection (identity mapping)
self.shortcut = nn.Sequential()
if in_channels != out_channels:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0),
nn.BatchNorm2d(out_channels)
)
def forward(self, x):
out = self.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x) # Adding the residual connection
out = self.relu(out)
return out
class ResPoseNet(nn.Module):
def __init__(self):
super(ResPoseNet, self).__init__()
# Using residual blocks for feature extraction
self.conv = nn.Sequential(
ResidualBlock(3, 32), # Initial Conv + Residual Block
nn.MaxPool2d(2, 2), # 112x112
ResidualBlock(32, 64), # Residual Block
nn.MaxPool2d(2, 2), # 56x56
ResidualBlock(64, 128), # Residual Block
nn.MaxPool2d(2, 2), # 28x28
ResidualBlock(128, 256), # Residual Block
nn.MaxPool2d(2, 2), # 28x28
ResidualBlock(256, 512), # Residual Block
nn.AdaptiveAvgPool2d((7, 7)) # 14x14 output
)
self.fc = nn.Sequential(
nn.Flatten(),
nn.Linear(512 * 7 * 7, 1024),
nn.ReLU(),
nn.Dropout(0.40),
nn.Linear(1024, 32), # Assuming 16 keypoints, each with x, y = 32 values
nn.Sigmoid() # Output keypoint coordinates between [0,1]
)
def forward(self, x):
x = self.conv(x)
x = self.fc(x)
return x
transform = transforms.Compose([
transforms.ToTensor(), # Convert to tensor (3, 224, 224)
transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) # Normalize RGB
]) |