CODEWITHSUNDEEP
pythondeep-learningneural-networkpytorchvgg-net
Maryam
Maryam

Reputation: 159

Sequential network with the VGG layers

I want to have a sequential network with the characteristics of VGG network (I want to pass my network to another function, which doesn't support VGG objects and supports nn.sequential).

I added the function getSequentialVersion method to VGG class to have the sequential network with the linear layer. However, apparently, there is a size mismatch in the network.

'''VGG for CIFAR10. FC layers are removed.
(c) YANG, Wei 
'''
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
import math


__all__ = [
    'VGG','vgg16_bn',
]


model_urls = {
    'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
}


class VGG(nn.Module):
    def __init__(self, features, num_classes=1000, cfg_type=None, batch_norm=False, **kwargs):
        super(VGG, self).__init__()
        self.features = features
        self.classifier = nn.Linear(512, num_classes)
        self._initialize_weights()
        self.cfg_type = cfg_type
        self.batch_norm = batch_norm

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

    def _initialize_weights(self):
        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))
                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):
                n = m.weight.size(1)
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()
            
    def getSequentialVersion(self):
        return make_layers(cfg[self.cfg_type], batch_norm=self.batch_norm, flag=True)


def make_layers(cfg, batch_norm=False, flag=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1, bias=False)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    if flag:
        #for Cifar10
        layers += [nn.Linear(512, 10)]
    return nn.Sequential(*layers)


cfg = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


def vgg16_bn(**kwargs):
    """VGG 16-layer model (configuration "D") with batch normalization"""
    print("VGG16-bn")
    model = VGG(make_layers(cfg['D'], batch_norm=True), cfg_type='D', batch_norm=True,**kwargs)
    return model

When I call summary(net, ( 3, 32, 32)) (for cifar10), I get the mismatch error. In other words, the main problem is when I add this line layers+= [nn.linear(512, 10)].

Can anyone help me? Thanks a lot.

The error message:

  File "./main.py", line 284, in <module>
    summary(net, ( 3, 32, 32))
  File "./anaconda3/envs/my_env/lib/python3.8/site-packages/torchsummary/torchsummary.py", line 72, in summary
    model(*x)
  File ".anaconda3/envs/my_env/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "./anaconda3/envs/my_env/lib/python3.8/site-packages/torch/nn/modules/container.py", line 119, in forward
    input = module(input)
  File "./anaconda3/envs/my_env/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "./anaconda3/envs/my_env/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 94, in forward
    return F.linear(input, self.weight, self.bias)
  File "./envs/my_env/lib/python3.8/site-packages/torch/nn/functional.py", line 1753, in linear
    return torch._C._nn.linear(input, weight, bias)
RuntimeError: mat1 dim 1 must match mat2 dim 0

Additional information: This is how exactly I initialize and use my network:

net = vgg16_bn(depth=args.depth,
                  num_classes=num_classes,
                  growthRate=args.growthRate,
                  compressionRate=args.compressionRate,
                  widen_factor=args.widen_factor,
                  dropRate=args.dropRate,
                  base_width=args.base_width,
                  cardinality=args.cardinality).getSequentialVersion()
net = net.to(args.device)    
module_names = ''
if hasattr(net, 'features'): 
    module_names = 'features'
elif hasattr(net, 'children'):
    module_names = 'children'
else:
    print('unknown net modules...')

summary(net, ( 3, 32, 32))

Upvotes: 0

Views: 310

Answers (1)

Berriel
Berriel

Reputation: 13601

The problem is quite simple. When flag=True (as in getSequentialVersion()), there's a missing Flatten operation. Therefore, to fix the problem, you need to add this operation like this:

if flag:
    # for Cifar10
    layers += [nn.Flatten(), nn.Linear(512, 10)]  # <<< add Flatten before Linear

In the forward call, you can see the flatten in its view form:

def forward(self, x):
    x = self.features(x)
    x = x.view(x.size(0), -1)  # here, equivalent to torch.flatten(x, 1)
    x = self.classifier(x)
    return x

and this is what was missing when you were transforming the layers to Sequential.

Upvotes: 1

Related Questions