File size: 2,594 Bytes
6028065 |
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 |
import torch
import torch.nn as nn
class ViolenceGRU(nn.Module):
def __init__(self):
super(ViolenceGRU, self).__init__()
# 2D CNN Backbone (Applied to each frame independently)
self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)
self.bn1 = nn.BatchNorm2d(32)
self.pool1 = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
self.bn2 = nn.BatchNorm2d(64)
self.pool2 = nn.MaxPool2d(2, 2)
self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
self.bn3 = nn.BatchNorm2d(128)
self.pool3 = nn.MaxPool2d(2, 2)
self.conv4 = nn.Conv2d(128, 256, kernel_size=3, padding=1)
self.bn4 = nn.BatchNorm2d(256)
self.pool4 = nn.MaxPool2d(2, 2)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
# Calculate feature dim after CNN
# Input: 112x112
# Pool1: 56x56
# Pool2: 28x28
# Pool3: 14x14
# Pool4: 7x7
self.feature_dim = 256 * 7 * 7
# GRU Layer
# input_size: Feature vector from CNN
# hidden_size: 256
# num_layers: 2
self.gru = nn.GRU(input_size=self.feature_dim, hidden_size=256, num_layers=2, batch_first=True, dropout=0.5)
self.fc = nn.Linear(256, 2) # Binary Classification
def forward(self, x):
# x shape from Dataset: (Batch, C, Seq, H, W)
b, c, s, h, w = x.size()
# Reshape for 2D CNN: (Batch * Seq, C, H, W)
x = x.permute(0, 2, 1, 3, 4).contiguous() # (B, S, C, H, W)
x = x.view(b * s, c, h, w)
# Pass through CNN
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)
# Flatten features: (Batch * Seq, Feature_Dim)
x = x.view(b * s, -1)
# Reshape for GRU: (Batch, Seq, Feature_Dim)
x = x.view(b, s, -1)
# GRU Pass
# out: (Batch, Seq, Hidden_Dim)
out, _ = self.gru(x)
# Take the last time step output for classification
out = out[:, -1, :]
out = self.dropout(out)
out = self.fc(out)
return out
|