LaNAS/Distributed_LaNAS/clientX/model.py [71:108]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def drop_path(x, drop_prob):
    if drop_prob > 0.:
        keep_prob = 1. - drop_prob

        mask = torch.cuda.FloatTensor(x.size(0), 1, 1, 1).bernoulli_(keep_prob)
        x.div_(keep_prob)
        try:
            x.mul_(mask)
        except:
            mask = torch.cuda.HalfTensor(x.size(0), 1, 1, 1).bernoulli_(keep_prob)
            x.mul_(mask)
    return x




class AuxiliaryHeadCIFAR(nn.Module):

    def __init__(self, C, num_classes):
        """assuming input size 8x8"""
        super(AuxiliaryHeadCIFAR, self).__init__()

        self.features = nn.Sequential(
            nn.ReLU(inplace=True),
            nn.AvgPool2d(5, stride=3, padding=0, count_include_pad=False),  # image size = 2 x 2
            nn.Conv2d(C, 128, 1, bias=False),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.Conv2d(128, 768, 2, bias=False),
            nn.BatchNorm2d(768),
            nn.ReLU(inplace=True)
        )
        self.classifier = nn.Linear(768, num_classes)

    def forward(self, x):
        x = self.features(x)
        x = self.classifier(x.view(x.size(0), -1))
        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



LaNAS/one-shot_LaNAS/Evaluate/individual_model.py [87:122]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def drop_path(x, drop_prob):
    if drop_prob > 0.:
        keep_prob = 1. - drop_prob

        mask = torch.cuda.FloatTensor(x.size(0), 1, 1, 1).bernoulli_(keep_prob)
        x.div_(keep_prob)
        try:
            x.mul_(mask)
        except:
            mask = torch.cuda.HalfTensor(x.size(0), 1, 1, 1).bernoulli_(keep_prob)
            x.mul_(mask)
    return x


class AuxiliaryHeadCIFAR(nn.Module):

    def __init__(self, C, num_classes):
        """assuming input size 8x8"""
        super(AuxiliaryHeadCIFAR, self).__init__()

        self.features = nn.Sequential(
            nn.ReLU(inplace=True),
            nn.AvgPool2d(5, stride=3, padding=0, count_include_pad=False),  # image size = 2 x 2
            nn.Conv2d(C, 128, 1, bias=False),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.Conv2d(128, 768, 2, bias=False),
            nn.BatchNorm2d(768),
            nn.ReLU(inplace=True)
        )
        self.classifier = nn.Linear(768, num_classes)

    def forward(self, x):
        x = self.features(x)
        x = self.classifier(x.view(x.size(0), -1))
        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -