oil/architectures/img_classifiers/vgg.py
"""
VGG model definition
ported from https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py
"""
import math
import torch.nn as nn
import torchvision.transforms as transforms
from ...utils.utils import Named
__all__ = ['VGG16', 'VGG16BN']
def make_layers(cfg, batch_norm=False):
layers = list()
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)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
cfg = {
16: [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
19: [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M',
512, 512, 512, 512, 'M'],
}
class VGG(nn.Module,metaclass=Named):
def __init__(self, num_targets=10, depth=16, batch_norm=False):
super(VGG, self).__init__()
self.features = make_layers(cfg[depth], batch_norm)
self.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(512, 512),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(512, 512),
nn.ReLU(True),
nn.Linear(512, num_targets),
)
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))
m.bias.data.zero_()
def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), -1)
x = self.classifier(x)
return x
class VGG16(VGG):
def __init__(self,num_targets=10):
super().__init__(num_targets=num_targets,depth=16,batch_norm=False)
class VGG16BN(VGG):
def __init__(self,num_targets=10):
super().__init__(num_targets=num_targets,depth=16,batch_norm=True)