Benchmarks

1
# Device config
2
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
3
​
4
# model
5
model = SimpleMLP(num_classes=10)
6
​
7
# Here we show all the MNIST variation we offer in the "classic" benchmarks
8
# benchmark = PermutedMNIST(n_experiences=5, seed=1)
9
benchmark = RotatedMNIST(n_experiences=5, rotations_list=[30, 60, 90, 120, 150], seed=1)
10
# benchmark = SplitMNIST(n_experiences=5, seed=1)
11
​
12
# choose some metrics and evaluation method
13
interactive_logger = InteractiveLogger()
14
​
15
eval_plugin = EvaluationPlugin(
16
    accuracy_metrics(minibatch=False, epoch=True, experience=True, stream=True),
17
    loss_metrics(minibatch=False, epoch=True, experience=True, stream=True),
18
    timing_metrics(epoch=True, epoch_running=True),
19
    cpu_usage_metrics(experience=True),
20
    ExperienceForgetting(),
21
    loggers=[interactive_logger])
22
​
23
# Than we can extract the parallel train and test streams
24
train_stream = benchmark.train_stream
25
test_stream = benchmark.test_stream
26
​
27
# Prepare for training & testing
28
optimizer = SGD(model.parameters(), lr=0.001, momentum=0.9)
29
criterion = CrossEntropyLoss()
30
​
31
# Continual learning strategy
32
cl_strategy = Naive(
33
    model, optimizer, criterion, train_mb_size=32, train_epochs=2,
34
    test_mb_size=32, device=device, evaluator=eval_plugin
35
)
36
​
37
# train and test loop
38
results = []
39
for train_task in train_stream:
40
    print("Current Classes: ", train_task.classes_in_this_experience)
41
    cl_strategy.train(train_task, num_workers=4)
42
    results.append(cl_strategy.eval(test_stream))
Copied!
🤝 Run it on Google Colab
You can run this chapter and play with it on Google Colaboratory:
Notebook currently unavailable.

Examples - Previous

Models

Next - Examples

Training

Last modified 3mo ago

Export as PDF

Copy link

Contents

🤝 Run it on Google Colab