I’m currently using a simple 3D network for binary classification, the model i’m using is:
import torch
import torch.nn as nn
class ConvModel(nn.Module):
def __init__(self, in_channels, num_classes):
super(ConvModel, self).__init__()
# conv3d (N, C, D, H, W)
self.conv1 = nn.Conv3d(in_channels=in_channels, out_channels=64, kernel_size=3, padding=1)
self.bn1 = nn.BatchNorm3d(num_features=64)
self.relu = nn.ReLU()
# square window stride=2
self.mpool = nn.MaxPool3d(kernel_size=3, stride=2, padding=1)
self.conv2 = nn.Conv3d(in_channels=64, out_channels=64, kernel_size=3, padding=1)
self.bn2 = nn.BatchNorm3d(num_features=64)
self.conv3 = nn.Conv3d(in_channels=64, out_channels=64, kernel_size=3, padding=1)
self.bn3 = nn.BatchNorm3d(num_features=64)
self.conv4 = nn.Conv3d(in_channels=64, out_channels=128, kernel_size=3, padding=1)
self.bn4 = nn.BatchNorm3d(num_features=128)
self.conv5 = nn.Conv3d(in_channels=128, out_channels=256, kernel_size=3, padding=1)
self.bn5 = nn.BatchNorm3d(256)
self.fc = nn.Linear(8*8*2*256, 512)
self.dropout = nn.Dropout(0.4)
self.dropout2 = nn.Dropout(0.3)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, num_classes)
self.flatten = nn.Flatten()
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.mpool(x)
x = self.conv2(x)
x = self.bn2(x)
x = self.relu(x)
x = self.mpool(x)
x = self.conv3(x)
x = self.bn3(x)
x = self.relu(x)
x = self.mpool(x)
x = self.conv4(x)
x = self.bn4(x)
x = self.relu(x)
x = self.mpool(x)
x = self.conv5(x)
x = self.bn5(x)
x = self.relu(x)
x = self.mpool(x)
x = self.flatten(x)
x = self.fc(x)
x = self.relu(x)
x = self.dropout(x)
x = self.fc2(x)
x = self.relu(x)
x = self.dropout2(x)
x = self.fc3(x)
return x
When training this with Adam (lr=1e-6), even after 50 epochs the model dosen’t generalise well and training loss with BCE is around 0.5-0.6. However if i remove the Dropout layers model overfits training data in 15 epochs with loss 0.01.
I’m not sure what kind of changes should i introduce to get my model to generalise, is using nn.Dropout3D something i should consider. I’ve been trying with different dropout probabilities but the best validations AUC ROC i get is 0.6 which can be just coz of randomness.
Anty help will be appreciated
Cheers