【Avalanche】基于pytorch的Continual Learning高效开发库demo测试

Avalanche是个用来做continual learning的end-to-end的库。作用是帮助研究者编写continual learning的程序。在保证了每个模块的完整性和独立性的基础上，保留了它们的扩展性和有效性，即使用者可以利用其框架编写自己的CL算法或导入自己的数据集。

官网：https://avalanche.continualai.org/
paper：https://arxiv.org/abs/2104.00405
github：https://github.com/ContinualAI/avalanche

对Continual Learning框架的定义：

整个过程可以看作对Continual Learning算法A的不断更新。所谓更新是指改变它内部的模型M和数据结构D。更新手段是使用一系列的不固定的经验流（e1,…, en）进行训练。更新的目标是让其在测试的经验流（e1t,…,ent）上的evaluation指标有更好的表现。

主要框架：

1. Benchmarks

		a. datasets：import现有的数据集
		b. classic benchmarks：经典的benchmarks
		c. generators：新建Benchmarks

2. Training

		a. Strategies：使用现有的continual learning方法或baselines 
			包括Naive, CWRStar, Replay, GDumb, Cumulative, LwF, GEM, AGEM, EWC, AR1
		b. Create Strategy：编写自己的strategy

3. Evaluation

		a. Evaluation: 使用Metrics和Loggers对模型进行评估和记录
		Metrics 包括Accuracy, Forgetting, Memory Usage, Running Times, etc.

代码demo，前面是每个模块的使用方法，最后一部分是测试example

################## 1. Benchmarks
# ---------------------------- 1.1 import datasets ---------------------------------------- #
from avalanche.benchmarks.datasets import MNIST, FashionMNIST, KMNIST, EMNIST, \
    QMNIST, FakeData, CocoCaptions, CocoDetection, LSUN, ImageNet, CIFAR10, \
    CIFAR100, STL10, SVHN, PhotoTour, SBU, Flickr8k, Flickr30k, VOCDetection, \
    VOCSegmentation, Cityscapes, SBDataset, USPS, HMDB51, UCF101, CelebA, \
    CORe50Dataset, TinyImagenet, CUB200, OpenLORIS, MiniImageNetDataset, \
    Stream51, CLEARDataset

# ---------------------------- 1.2 classic benchmarks ---------------------------------------- #
from avalanche.benchmarks.classic import CORe50, SplitTinyImageNet, SplitCIFAR10, \
    SplitCIFAR100, SplitCIFAR110, SplitMNIST, RotatedMNIST, PermutedMNIST, SplitCUB200

# creating the benchmark (scenario object)
perm_mnist = PermutedMNIST(
    n_experiences=3,
    seed=1234,
)

# recovering the train and test streams
train_stream = perm_mnist.train_stream
test_stream = perm_mnist.test_stream

# iterating over the train stream
for experience in train_stream:
    print("Start of task ", experience.task_label)
    print('Classes in this task:', experience.classes_in_this_experience)

    # The current Pytorch training set can be easily recovered through the
    # experience
    current_training_set = experience.dataset
    # ...as well as the task_label
    print('Task {}'.format(experience.task_label))
    print('This task contains', len(current_training_set), 'training examples')

    # we can recover the corresponding test experience in the test stream
    current_test_set = test_stream[experience.current_experience].dataset
    print('This task contains', len(current_test_set), 'test examples')


# ---------------------------- 1.3 benchmarks generators ---------------------------------------- #
from avalanche.benchmarks.generators import nc_benchmark, ni_benchmark
from torchvision.datasets import MNIST

mnist_train = MNIST('.', train=True, download=True)
mnist_test = MNIST('.', train=False)

benchmark = ni_benchmark(
    mnist_train, mnist_test, n_experiences=10, shuffle=True, seed=1234,
    balance_experiences=True
)
benchmark = nc_benchmark(
    mnist_train, mnist_test, n_experiences=10, shuffle=True, seed=1234,
    task_labels=False
)

# ---------------------------- 1.4 generic generators ---------------------------------------- #
from avalanche.benchmarks.generators import filelist_benchmark, dataset_benchmark, \
                                            tensors_benchmark, paths_benchmark

################## 2. Training
# ---------------------------- 2.1 strategies ---------------------------------------- #
from avalanche.models import SimpleMLP
from avalanche.training import Naive, CWRStar, Replay, GDumb, \
    Cumulative, LwF, GEM, AGEM, EWC, AR1
from torch.optim import SGD
from torch.nn import CrossEntropyLoss

model = SimpleMLP(num_classes=10)
cl_strategy = Naive(
    model, SGD(model.parameters(), lr=0.001, momentum=0.9),
    CrossEntropyLoss(), train_mb_size=100, train_epochs=4, eval_mb_size=100
)

# ---------------------------- 2.2 create new strategy ---------------------------------------- #
from torch.utils.data import DataLoader

class MyStrategy():
    """My Basic Strategy"""

    def __init__(self, model, optimizer, criterion):
        self.model = model
        self.optimizer = optimizer
        self.criterion = criterion

    def train(self, experience):
        # here you can implement your own training loop for each experience (i.e.
        # batch or task).

        train_dataset = experience.dataset
        t = experience.task_label
        train_data_loader = DataLoader(
            train_dataset, num_workers=4, batch_size=128
        )

        for epoch in range(1):
            for mb in train_data_loader:
                # you magin here...
                pass

    def eval(self, experience):
        # here you can implement your own eval loop for each experience (i.e.
        # batch or task).

        eval_dataset = experience.dataset
        t = experience.task_label
        eval_data_loader = DataLoader(
            eval_dataset, num_workers=4, batch_size=128
        )

        # eval here
# ---------------------------- 2.2 create new strategy - use it ---------------------------------------- #
from avalanche.models import SimpleMLP
from avalanche.benchmarks import SplitMNIST

# Benchmark creation
benchmark = SplitMNIST(n_experiences=5)

# Model Creation
model = SimpleMLP(num_classes=benchmark.n_classes)

# Create the Strategy Instance (MyStrategy)
cl_strategy = MyStrategy(
    model, SGD(model.parameters(), lr=0.001, momentum=0.9),
    CrossEntropyLoss())

# Training Loop
print('Starting experiment...')

for exp_id, experience in enumerate(benchmark.train_stream):
    print("Start of experience ", experience.current_experience)

    cl_strategy.train(experience)
    print('Training completed')

    print('Computing accuracy on the current test set')
    cl_strategy.eval(benchmark.test_stream[exp_id])



################## 3. Evaluation
# utility functions to create plugin metrics
from avalanche.evaluation.metrics import accuracy_metrics, loss_metrics, forgetting_metrics
from avalanche.logging import InteractiveLogger, TensorboardLogger
from avalanche.training.plugins import EvaluationPlugin

eval_plugin = EvaluationPlugin(
    # accuracy after each training epoch
    # and after each evaluation experience
    accuracy_metrics(epoch=True, experience=True),
    # loss after each training minibatch and each
    # evaluation stream
    loss_metrics(minibatch=True, stream=True),
    # catastrophic forgetting after each evaluation
    # experience
    forgetting_metrics(experience=True, stream=True),
    # add as many metrics as you like
    loggers=[InteractiveLogger(), TensorboardLogger()])

# pass the evaluation plugin instance to the strategy
# strategy = EWC(..., evaluator=eval_plugin)

# THAT'S IT!!



# ---------------------------- Example ---------------------------------------- #
from avalanche.benchmarks.classic import SplitMNIST
from avalanche.evaluation.metrics import forgetting_metrics, accuracy_metrics,\
    loss_metrics, timing_metrics, cpu_usage_metrics, StreamConfusionMatrix,\
    disk_usage_metrics, gpu_usage_metrics
from avalanche.models import SimpleMLP
from avalanche.logging import InteractiveLogger, TextLogger, TensorboardLogger
from avalanche.training.plugins import EvaluationPlugin
from avalanche.training import Naive

from torch.optim import SGD
from torch.nn import CrossEntropyLoss

benchmark = SplitMNIST(n_experiences=5)

# MODEL CREATION
model = SimpleMLP(num_classes=benchmark.n_classes)

# DEFINE THE EVALUATION PLUGIN and LOGGERS
# The evaluation plugin manages the metrics computation.
# It takes as argument a list of metrics, collectes their results and returns
# them to the strategy it is attached to.

# log to Tensorboard
tb_logger = TensorboardLogger()

# log to text file
text_logger = TextLogger(open('log.txt', 'a'))

# print to stdout
interactive_logger = InteractiveLogger()

eval_plugin = EvaluationPlugin(
    accuracy_metrics(minibatch=True, epoch=True, experience=True, stream=True),
    loss_metrics(minibatch=True, epoch=True, experience=True, stream=True),
    timing_metrics(epoch=True),
    cpu_usage_metrics(experience=True),
    forgetting_metrics(experience=True, stream=True),
    StreamConfusionMatrix(num_classes=benchmark.n_classes, save_image=False),
    disk_usage_metrics(minibatch=True, epoch=True, experience=True, stream=True),
    loggers=[interactive_logger, text_logger, tb_logger]
)

# CREATE THE STRATEGY INSTANCE (NAIVE)
cl_strategy = Naive(
    model, SGD(model.parameters(), lr=0.001, momentum=0.9),
    CrossEntropyLoss(), train_mb_size=500, train_epochs=1, eval_mb_size=100,
    evaluator=eval_plugin)

# TRAINING LOOP
print('Starting experiment...')
results = []
for experience in benchmark.train_stream:
    print("Start of experience: ", experience.current_experience)
    print("Current Classes: ", experience.classes_in_this_experience)

    # train returns a dictionary which contains all the metric values
    res = cl_strategy.train(experience, num_workers=4)
    print('Training completed')

    print('Computing accuracy on the whole test set')
    # eval also returns a dictionary which contains all the metric values
    results.append(cl_strategy.eval(benchmark.test_stream, num_workers=4))

报错与解决：

1. TypeError: No loop matching the specified signature and casting was found for ufunc greater
   解决：降低numpy版本从1.24到1.22
2. The “freeze_support()” line can be omitted if the program is not going to be frozen to produce an executable.
   参考issue
   解决：将num_workers设置为num_workers=0