models/alexnet.py [65:76]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                for i in range(m.out_channels):
                    m.weight.data[i].normal_(0, math.sqrt(2. / n))
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



models/vgg16.py [59:71]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if isinstance(m, nn.Conv2d):
                #print(y)
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                for i in range(m.out_channels):
                    m.weight.data[i].normal_(0, math.sqrt(2. / n))
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -