Why am I always stuck at the first step of adversarial training?

[Rabbit0121]

This is my code.

import torch
import sys
import torch
sys.path.append('..')
sys.path.append('../..')
from data.data_utils_1 import get_loader
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
from art.attacks.evasion import ProjectedGradientDescent
from art.estimators.classification import PyTorchClassifier
from art.defences.trainer import AdversarialTrainer
import torch
import numpy as np
from torch.optim.lr_scheduler import StepLR

model = torch.load((f'xxx/cifar10/r50_1x_sk0_pretrain.pth'))
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9, weight_decay=5e-4)
classifier = PyTorchClassifier(
    model=model,
    clip_values=(0.0, 1.0),
    loss = torch.nn.CrossEntropyLoss(label_smoothing=0.1),
    optimizer = optimizer,
    # scheduler = scheduler,
    input_shape=(3, 224, 224),    
    nb_classes=10, 
)

train_loader, test_loader, val_loader = get_loader('cifar10', 128, 1, 4, False)

attack = ProjectedGradientDescent(
    estimator=classifier,
    norm=np.inf,
    eps=8/255,
    eps_step=2/255,
    max_iter=7,
    targeted=False,
    verbose=True,
)
from art.data_generators import PyTorchDataGenerator
generator = PyTorchDataGenerator(train_loader, size=40000, batch_size=128)
trainer = AdversarialTrainer(classifier=classifier, attacks = attack, ratio=1.0) 

trainer.fit_generator(generator, nb_epochs=100)

And this is the code of get_loader

elif(dataset == 'cifar10'):
            test_dataset = torchvision.datasets.CIFAR10(root='/data4/xxx/cifar', train=False, transform=test_transform_used, download=False)
            train_dataset = torchvision.datasets.CIFAR10(root='/data4/xxx/cifar', train=True, transform=train_transform_used, download=False)
            train_dataset, _ = random_split(train_dataset, [int(percent*len(train_dataset)), len(train_dataset)-int(percent*len(train_dataset))])
            train_size = int(0.8 * len(train_dataset))
            val_size = len(train_dataset) - train_size
            train_dataset, val_dataset = random_split(train_dataset, [train_size, val_size])
val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False, num_workers=num_workers)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=num_workers)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=num_workers)
...
return train_loader, test_loader, val_loader

The transform is:

train_transform_without_normalize = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.RandomHorizontalFlip(p=0.5),
    transforms.RandomRotation(degrees=45),
    # transforms.Lambda(lambda x: x.repeat(3,1,1))
    # transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

It has been like this for a long time.

[beat-buesser]

Hi @Rabbit0121 Are your CPUs and GPUs busy or idling in that state? Can you share the stack trace shown when abort the program?