model.py

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