def make_layers(cfg, batch_norm=False):
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [my_MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = my_Conv2d(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, my_BatchNorm2d(v), my_ReLU(inplace=True)]
else:
layers += [conv2d, my_ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
def __init__(self, features, num_classes=1000, init_weights=True):
super(my_VGG, self).__init__(features,
num_classes=num_classes,
init_weights=init_weights)
self.features = features
#self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
self.avgpool = my_AvgPool2d(kernel_size=1, stride=1)
self.classifier = nn.Sequential(
my_Linear(512 * 7 * 7, 4096),
# my_Linear(36, 4096),
my_ReLU(True),
nn.Dropout(),
my_Linear(4096, 4096),
my_ReLU(True),
nn.Dropout(),
my_Linear(4096, num_classes),
)
self._layers = None
self._verbose = True
if init_weights:
self._initialize_weights()
def __init__(self, in_channels, num_classes, conv_block=None):
super(InceptionAux, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.avgpool = my_AdaptiveAvgPool2d((4,4))
self.conv = conv_block(in_channels, 128, kernel_size=1)
self.relu = my_ReLU(inplace=True)
self.fc1 = my_Linear(2048, 1024)
self.fc2 = my_Linear(1024, num_classes)
self._mode = 0
def __init__(self, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = my_Conv2d(in_channels, out_channels, bias=False, **kwargs)
self.bn = my_BatchNorm2d(out_channels, eps=0.001)
self.relu = my_ReLU(inplace=True)
self._mode = 0
