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, vgg_name):
super(my_VGG, self).__init__(vgg_name)
self.features = self._make_layers(my_cfg[vgg_name])
# self.classifier = my_Linear(25088, 4096)
self.classifier = my_Linear(64, 20)
###!!! Mandatory variables
# _layers
self._layers = None
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, num_classes=1000, aux_logits=True, transform_input=False, init_weights=True,
blocks=None):
super(GoogLeNet, self).__init__()
if blocks is None:
blocks = [BasicConv2d, Inception, InceptionAux]
assert len(blocks) == 3
conv_block = blocks[0]
inception_block = blocks[1]
inception_aux_block = blocks[2]
self.aux_logits = aux_logits
self.transform_input = transform_input
self.conv1 = conv_block(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = my_MaxPool2d(3, stride=2, ceil_mode=True)
self.conv2 = conv_block(64, 64, kernel_size=1)
self.conv3 = conv_block(64, 192, kernel_size=3, padding=1)
self.maxpool2 = my_MaxPool2d(3, stride=2, ceil_mode=True)
self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32)
self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = my_MaxPool2d(3, stride=2, ceil_mode=True)
self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64)
self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64)
self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64)
self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64)
self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = my_MaxPool2d(2, stride=2, ceil_mode=True)
self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128)
self.inception5b = inception_block(832, 384, 192, 384, 48, 128, 128)
##!! Mandatory variables
self._layers = None
if aux_logits:
self.aux1 = inception_aux_block(512, num_classes)
self.aux2 = inception_aux_block(528, num_classes)
self.avgpool = my_AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(0.2)
self.fc = my_Linear(1024, num_classes)
if init_weights:
self._initialize_weights()
def __init__(self,
block,
layers,
num_classes=1000,
zero_init_residual=False,
groups=1,
width_per_group=64,
replace_stride_with_dilation=None,
norm_layer=None):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = my_BatchNorm2d
self._norm_layer = norm_layer
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
# each element in the tuple indicates if we should replace
# the 2x2 stride with a dilated convolution instead
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(
replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = my_Conv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = my_ReLU(inplace=True)
self.maxpool = my_MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block,
128,
layers[1],
stride=2,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=2,
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block,
512,
layers[3],
stride=2,
dilate=replace_stride_with_dilation[2])
self.avgpool = my_AdaptiveAvgPool2d((1, 1))
#self.avgpool = my_AdaptiveAvgPool2d(1)
self.fc = my_Linear(512 * block.expansion, num_classes)
##!! Mandatory variables
self._layers = None
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)