Spaces:
Sleeping
Sleeping
File size: 1,536 Bytes
8495359 | 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 | import torch
import torch.nn as nn
class FaceDetectionMultiBoxCNN(nn.Module):
def __init__(self, S=20, B=3):
super().__init__()
self.S = S
self.B = B
self.output_size = S * S * B * 5 # (x, y, w, h, confidence)
self.features = nn.Sequential(
nn.Conv2d(3, 32, 3, 1, 1),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(2), # 320->160
nn.Conv2d(32, 64, 3, 1, 1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(2), # 160->80
nn.Conv2d(64, 128, 3, 1, 1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(2), # 80->40
nn.Conv2d(128, 256, 3, 1, 1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.MaxPool2d(2), # 40->20
nn.Conv2d(256, 512, 3, 1, 1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.MaxPool2d(2), # 20->10
)
# Calculate flatten size dynamically
dummy = torch.zeros(1, 3, 320, 320)
with torch.no_grad():
dummy_out = self.features(dummy)
flatten_size = dummy_out.view(1, -1).shape[1]
self.classifier = nn.Sequential(
nn.Flatten(),
nn.Linear(flatten_size, 1024),
nn.ReLU(),
nn.Linear(1024, self.output_size)
)
def forward(self, x):
x = self.features(x)
x = self.classifier(x)
return x.view(-1, self.S, self.S, self.B * 5)
|