Core Dumped: Modify Parameters Manually

For every layer of ResNet, I would like to assign the average value of convs to each conv, every time after they’re updated by backward.

class ResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=10):...
    def _make_layer(self, block, planes, num_blocks, stride):...
    def forward(self, x):...

    def setAvg(self):
        for layer in [self.layer1,self.layer2,self.layer3,self.layer4]:
            weight_conv_average = torch.mean(
                torch.stack([torch.Tensor(p) for n, p in layer.named_parameters() if 'conv' in n and (p.size()[0]==p.size()[1])]), 0)
            for n, p in layer.named_parameters():
                if 'conv' in n and (p.size()[0]==p.size()[1]):
                    #print(n,'      ', p.size())

And in the main part of training, I use

rawnet = ResNet18()
net =
if device == 'cuda':
    net = torch.nn.DataParallel(net)
    cudnn.benchmark = True
def train(epoch):
    with torch.no_grad():

However this will cause Segmentation fault (core dumped) with Linux cuda env.

I’ve tried to invoke setAvg in forward but also failed.

And the reason why I distinguish net and rawnet is that net is DataParallel object, which has no attribute 'setAvg'.

Big Thanks!

I’ve figured it out:

1.use net.module.setAvg to deal with attributes for DataParalleled net need to call torch.Tensor(p) for Parameter p, just p is ok