return 1
length = max - min
num_repeat = (weight - min) * (range_right - 1) / length + 1
return num_repeat
trainset = torchvision.datasets.MNIST('./data',
train=True,
download=True,
transform=transforms.ToTensor())
trainloader = torch.utils.data.DataLoader(dataset=trainset, shuffle=False)
CLASSIFIER_NUM = 9
classifier = AdaBoostClassifier(mlpClassifier)
classifier.train(trainloader, classifier_num=CLASSIFIER_NUM)
test_dataset = torchvision.datasets.MNIST(root='./data',
train=False,
download=True,
transform=transforms.ToTensor())
test_dataloader = torch.utils.data.DataLoader(test_dataset, shuffle=False)
# Test the AdaBoostClassifier
correct = 0
for batch_index, (data, target) in enumerate(test_dataloader):
# Copy data to GPU if needed
data = data.to(device)
target = target.to(device)
category = classifier.predict(data)
])
trainset = torchvision.datasets.CIFAR10(root='./data',
train=True,
download=True,
transform=transform_train)
train_dataloader = torch.utils.data.DataLoader(trainset,
batch_size=BATCH_SIZE,
shuffle=False)
validation_dataloader = torch.utils.data.DataLoader(trainset,
batch_size=1,
shuffle=False)
# Define and train the AdaBoostClassifier
classifier = AdaBoostClassifier(ResNetBibdGcClassifier)
classifier.train(train_dataloader,
validation_dataloader,
classifier_num=CLASSIFIER_NUM)
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
test_dataset = torchvision.datasets.CIFAR10(root='./data',
train=False,
download=True,
transform=transform_test)
test_dataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
shuffle=False)
# Test the AdaBoostClassifier
