Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub

Model Configuration
1 torch.manual_seed(13)
2 model_cnn1 = nn.Sequential()
3
4 # Featurizer
5 # Block 1: 1@10x10 -> n_channels@8x8 -> n_channels@4x4
6 n_channels = 1
7 model_cnn1.add_module('conv1', nn.Conv2d(
8 in_channels=1, out_channels=n_channels, kernel_size=3
9 ))
10 model_cnn1.add_module('relu1', nn.ReLU())
11 model_cnn1.add_module('maxp1', nn.MaxPool2d(kernel_size=2))
12 # Flattening: n_channels _ 4 _ 4
13 model_cnn1.add_module('flatten', nn.Flatten())
14
15 # Classification
16 # Hidden Layer
17 model_cnn1.add_module('fc1',
18 nn.Linear(in_features=n_channels*4*4, out_features=10)
19 )
20 model_cnn1.add_module('relu2', nn.ReLU())
21 # Output Layer
22 model_cnn1.add_module('fc2',
23 nn.Linear(in_features=10, out_features=3)
24 )
25
26 lr = 0.1
27 multi_loss_fn = nn.CrossEntropyLoss(reduction='mean')
28 optimizer_cnn1 = optim.SGD(model_cnn1.parameters(), lr=lr)
Model Training
1 sbs_cnn1 = StepByStep(model_cnn1, multi_loss_fn, optimizer_cnn1)
2 sbs_cnn1.set_loaders(train_loader, val_loader)
3 sbs_cnn1.train(20)
Visualizing Filters
fig_filters = sbs_cnn1.visualize_filters('conv1', cmap='gray')
412 | Chapter 5: Convolutions