File size: 2,042 Bytes
0e6cabe |
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 |
import torch
import torch.nn as nn
class ViolenceConv3D(nn.Module):
def __init__(self):
super(ViolenceConv3D, self).__init__()
# 4-Layer Conv3D Architecture
# Input: (Batch, 3, 16, 112, 112)
self.conv1 = nn.Conv3d(3, 32, kernel_size=(3, 3, 3), padding=(1, 1, 1))
self.bn1 = nn.BatchNorm3d(32)
self.pool1 = nn.MaxPool3d(kernel_size=(1, 2, 2), stride=(1, 2, 2))
self.conv2 = nn.Conv3d(32, 64, kernel_size=(3, 3, 3), padding=(1, 1, 1))
self.bn2 = nn.BatchNorm3d(64)
self.pool2 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2))
self.conv3 = nn.Conv3d(64, 128, kernel_size=(3, 3, 3), padding=(1, 1, 1))
self.bn3 = nn.BatchNorm3d(128)
self.pool3 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2))
self.conv4 = nn.Conv3d(128, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1))
self.bn4 = nn.BatchNorm3d(256)
self.pool4 = nn.MaxPool3d(kernel_size=(2, 2, 2), stride=(2, 2, 2))
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
# Calculate Flatten Size dynamically based on architecture logic
# P1: 16 x 56 x 56
# P2: 8 x 28 x 28
# P3: 4 x 14 x 14
# P4: 2 x 7 x 7
self.flatten_dim = 256 * 2 * 7 * 7
self.fc1 = nn.Linear(self.flatten_dim, 512)
self.fc2 = nn.Linear(512, 2) # Binary Classification (Violence vs No-Violence)
def forward(self, x):
x = self.relu(self.bn1(self.conv1(x)))
x = self.pool1(x)
x = self.relu(self.bn2(self.conv2(x)))
x = self.pool2(x)
x = self.relu(self.bn3(self.conv3(x)))
x = self.pool3(x)
x = self.relu(self.bn4(self.conv4(x)))
x = self.pool4(x)
x = x.view(x.size(0), -1)
x = self.dropout(self.relu(self.fc1(x)))
x = self.fc2(x)
return x
|