I was to attack a model with adversarial examples
and got IndexError : tuple index out of range during backward pass
35 # Calculate gradients of model in backward pass
---> 36 loss.backward()
37
38 # Collect datagrad
~/anaconda3/envs/yoon/lib/python3.6/site-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph)
116 products. Defaults to ``False``.
117 """
--> 118 torch.autograd.backward(self, gradient, retain_graph, create_graph)
119
120 def register_hook(self, hook):
~/anaconda3/envs/yoon/lib/python3.6/site-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables)
91 Variable._execution_engine.run_backward(
92 tensors, grad_tensors, retain_graph, create_graph,
---> 93 allow_unreachable=True) # allow_unreachable flag
94
95
~/anaconda3/envs/yoon/lib/python3.6/site-packages/torch/autograd/function.py in apply(self, *args)
75
76 def apply(self, *args):
---> 77 return self._forward_cls.backward(self, *args)
78
79
~/Block-wise-Scrambled-Image-Recognition/shakedrop.py in backward(ctx, grad_output)
25 @staticmethod
26 def backward(ctx, grad_output):
---> 27 gate = ctx.saved_tensors[0]
28 if gate.item() == 0:
29 beta = torch.cuda.FloatTensor(grad_output.size(0)).uniform_(0, 1)
IndexError: tuple index out of range
but I can get loss value
fgsm
output is tensor([[-1.0937, -2.6928, 1.2549, 2.1249, 1.4102, 2.1192, 1.3507, -0.2068,
-1.5742, -2.8067]], device='cuda:0', grad_fn=<AddmmBackward>)
target is tensor([3], device='cuda:0')
tensor(-2.1249, device='cuda:0', grad_fn=<NllLossBackward>)
test code was this ( batch size is 1 to check if original input is classified well )
def test( model, device, test_loader, epsilon, attack_name ):
# Accuracy counter
correct = 0
adv_examples = []
print(attack_name)
# Loop over all examples in test set
for data, target in test_loader:
# Send the data and label to the device
data, target = data.to(device), target.to(device)
# Set requires_grad attribute of tensor. Important for Attack
data.requires_grad = True
# Forward pass the data through the model
output = model(data)
print("output is",output)
print("target is", target)
init_pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
# If the initial prediction is wrong, dont bother attacking, just move on
if init_pred.item() != target.item():
continue
# Calculate the loss
loss = F.nll_loss(output, target)
print(loss)
# Zero all existing gradients
model.zero_grad()
an
# Calculate gradients of model in backward pass
loss.backward()
# Collect datagrad
data_grad = data.grad.data
# Call attack
dataset is cifar10
and I used model pyramidnet
class ShakeBasicBlock(nn.Module):
def __init__(self, in_ch, out_ch, stride=1, p_shakedrop=1.0):
super(ShakeBasicBlock, self).__init__()
self.downsampled = stride == 2
self.branch = self._make_branch(in_ch, out_ch, stride=stride)
self.shortcut = not self.downsampled and None or nn.AvgPool2d(2)
self.shake_drop = ShakeDrop(p_shakedrop)
def forward(self, x):
h = self.branch(x)
h = self.shake_drop(h)
h0 = x if not self.downsampled else self.shortcut(x)
pad_zero = Variable(torch.zeros(h0.size(0), h.size(1) - h0.size(1), h0.size(2), h0.size(3)).float()).cuda()
h0 = torch.cat([h0, pad_zero], dim=1)
return h + h0
def _make_branch(self, in_ch, out_ch, stride=1):
return nn.Sequential(
nn.BatchNorm2d(in_ch),
nn.Conv2d(in_ch, out_ch, 3, padding=1, stride=stride, bias=False),
nn.BatchNorm2d(out_ch),
nn.ReLU(inplace=True),
nn.Conv2d(out_ch, out_ch, 3, padding=1, stride=1, bias=False),
nn.BatchNorm2d(out_ch))
class ShakePyramidNet(nn.Module):
def __init__(self, depth=110, alpha=270, label=10):
super(ShakePyramidNet, self).__init__()
in_ch = 16
# for BasicBlock
n_units = (depth - 2) // 6
in_chs = [in_ch] + [in_ch + math.ceil((alpha / (3 * n_units)) * (i + 1)) for i in range(3 * n_units)]
block = ShakeBasicBlock
self.in_chs, self.u_idx = in_chs, 0
self.ps_shakedrop = [1 - (1.0 - (0.5 / (3 * n_units)) * (i + 1)) for i in range(3 * n_units)]
self.c_in = nn.Conv2d(3, in_chs[0], 3, padding=1)
self.bn_in = nn.BatchNorm2d(in_chs[0])
self.layer1 = self._make_layer(n_units, block, 1)
self.layer2 = self._make_layer(n_units, block, 2)
self.layer3 = self._make_layer(n_units, block, 2)
self.bn_out = nn.BatchNorm2d(in_chs[-1])
self.fc_out = nn.Linear(in_chs[-1], label)
# Initialize paramters
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
elif isinstance(m, nn.Linear):
m.bias.data.zero_()
def forward(self, x):
h = self.bn_in(self.c_in(x))
feature = h
h = self.layer1(h)
h = self.layer2(h)
h = self.layer3(h)
h = F.relu(self.bn_out(h))
h = F.avg_pool2d(h, 8)
h = h.view(h.size(0), -1)
h = self.fc_out(h)
return h
def _make_layer(self, n_units, block, stride=1):
layers = []
for i in range(int(n_units)):
layers.append(block(self.in_chs[self.u_idx], self.in_chs[self.u_idx+1],
stride, self.ps_shakedrop[self.u_idx]))
self.u_idx, stride = self.u_idx + 1, 1
return nn.Sequential(*layers)
Do you know how to solve this problem?