def __init__(self, version='1_0', num_classes=100):
super(SqueezeNet, self).__init__()
self.num_classes = num_classes
if version == '1_0':
self.features = nn.Sequential(
nn.Conv2D(3, 96, kernel_size=3, stride=1),
nn.ReLU(),
nn.MaxPool2D(kernel_size=3, stride=2, ceil_mode=True),
Fire(96, 16, 64, 64),
Fire(128, 16, 64, 64),
Fire(128, 32, 128, 128),
nn.MaxPool2D(kernel_size=3, stride=2, ceil_mode=True),
Fire(256, 32, 128, 128),
Fire(256, 48, 192, 192),
Fire(384, 48, 192, 192),
Fire(384, 64, 256, 256),
nn.MaxPool2D(kernel_size=3, stride=2, ceil_mode=True),
Fire(512, 64, 256, 256),
)
elif version == '1_1':
self.features = nn.Sequential(
nn.Conv2D(3, 64, kernel_size=3, stride=1),
nn.ReLU(),
nn.MaxPool2D(kernel_size=3, stride=2, ceil_mode=True),
Fire(64, 16, 64, 64),
Fire(128, 16, 64, 64),
nn.MaxPool2D(kernel_size=3, stride=2, ceil_mode=True),
Fire(128, 32, 128, 128),
Fire(256, 32, 128, 128),
nn.MaxPool2D(kernel_size=3, stride=2, ceil_mode=True),
Fire(256, 48, 192, 192),
Fire(384, 48, 192, 192),
Fire(384, 64, 256, 256),
Fire(512, 64, 256, 256),
)
else:
# FIXME: Is this needed? SqueezeNet should only be called from the
# FIXME: squeezenet1_x() functions
# FIXME: This checking is not done for the other models
raise ValueError("Unsupported SqueezeNet version {version}:"
"1_0 or 1_1 expected".format(version=version))
# Final convolution is initialized differently from the rest
final_conv = nn.Conv2D(512, self.num_classes, kernel_size=1)
self.classifier = nn.Sequential(nn.Dropout(p=0.5),
final_conv, nn.ReLU(),
nn.AdaptiveAvgPool2d((1, 1)))
def __init__(self, num_channels, num_filters, reduction_ratio, name=None):
super(SELayer, self).__init__()
self.pool2d_gap = nn.AdaptiveAvgPool2d(1)
self._num_channels = num_channels
med_ch = int(num_channels / reduction_ratio)
stdv = 1.0 / math.sqrt(num_channels * 1.0)
self.squeeze = nn.Linear(
num_channels,
med_ch,
act="relu",
param_attr=paddle.ParamAttr(
initializer=nn.initializer.Uniform(-stdv, stdv)))
stdv = 1.0 / math.sqrt(med_ch * 1.0)
self.excitation = nn.Linear(
med_ch,
num_filters,
act="sigmoid",
param_attr=paddle.ParamAttr(
initializer=nn.initializer.Uniform(-stdv, stdv)))
def __init__(self,
inverted_residual_setting,
last_channel,
num_classes=1000,
block=None,
norm_layer=None,
**kwargs):
"""
MobileNet V3 main class
Args:
inverted_residual_setting (List[InvertedResidualConfig]): Network structure
last_channel (int): The number of channels on the penultimate layer
num_classes (int): Number of classes
block (Optional[Callable[..., nn.Layer]]): Module specifying inverted residual building block for mobilenet
norm_layer (Optional[Callable[..., nn.Layer]]): Module specifying the normalization layer to use
"""
super().__init__()
if not inverted_residual_setting:
raise ValueError(
"The inverted_residual_setting should not be empty")
elif not (isinstance(inverted_residual_setting, Sequence) and all([
isinstance(s, InvertedResidualConfig)
for s in inverted_residual_setting
])):
raise TypeError(
"The inverted_residual_setting should be List[InvertedResidualConfig]"
)
if block is None:
block = InvertedResidual
if norm_layer is None:
norm_layer = partial(nn.BatchNorm2d, eps=0.001, momentum=0.01)
layers = []
# building first layer
firstconv_output_channels = inverted_residual_setting[0].input_channels
layers.append(
ConvBNActivation(3,
firstconv_output_channels,
kernel_size=3,
stride=2,
norm_layer=norm_layer,
activation_layer=nn.Hardswish))
# building inverted residual blocks
for cnf in inverted_residual_setting:
layers.append(block(cnf, norm_layer))
# building last several layers
lastconv_input_channels = inverted_residual_setting[-1].out_channels
lastconv_output_channels = 6 * lastconv_input_channels
layers.append(
ConvBNActivation(lastconv_input_channels,
lastconv_output_channels,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Hardswish))
self.features = nn.Sequential(*layers)
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.classifier = nn.Sequential(
nn.Linear(lastconv_output_channels, last_channel),
nn.Hardswish(),
nn.Dropout(p=0.2, ),
nn.Linear(last_channel, num_classes),
)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out')
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def __init__(
self,
num_classes=100,
aux_logits=True,
transform_input=False,
inception_blocks=None,
init_weights=None
):
super(Inception3, self).__init__()
if inception_blocks is None:
inception_blocks = [
BasicConv2d, InceptionA, InceptionB, InceptionC,
InceptionD, InceptionE, InceptionAux
]
if init_weights is None:
warnings.warn('The default weight initialization of inception_v3 will be changed in future releases of '
'torchvision. If you wish to keep the old behavior (which leads to long initialization times'
' due to scipy/scipy#11299), please set init_weights=True.', FutureWarning)
init_weights = True
assert len(inception_blocks) == 7
conv_block = inception_blocks[0]
inception_a = inception_blocks[1]
inception_b = inception_blocks[2]
inception_c = inception_blocks[3]
inception_d = inception_blocks[4]
inception_e = inception_blocks[5]
inception_aux = inception_blocks[6]
self.aux_logits = aux_logits
self.transform_input = transform_input
self.Conv2d_1a_3x3 = conv_block(3, 32, kernel_size=3, stride=2)
self.Conv2d_2a_3x3 = conv_block(32, 32, kernel_size=3)
self.Conv2d_2b_3x3 = conv_block(32, 64, kernel_size=3, padding=1)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2)
self.Conv2d_3b_1x1 = conv_block(64, 80, kernel_size=1)
self.Conv2d_4a_3x3 = conv_block(80, 192, kernel_size=3)
self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2)
self.Mixed_5b = inception_a(192, pool_features=32)
self.Mixed_5c = inception_a(256, pool_features=64)
self.Mixed_5d = inception_a(288, pool_features=64)
self.Mixed_6a = inception_b(288)
self.Mixed_6b = inception_c(768, channels_7x7=128)
self.Mixed_6c = inception_c(768, channels_7x7=160)
self.Mixed_6d = inception_c(768, channels_7x7=160)
self.Mixed_6e = inception_c(768, channels_7x7=192)
self.AuxLogits = None
if aux_logits:
self.AuxLogits = inception_aux(768, num_classes)
self.Mixed_7a = inception_d(768)
self.Mixed_7b = inception_e(1280)
self.Mixed_7c = inception_e(2048)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout()
self.fc = nn.Linear(2048, num_classes)
if init_weights:
for m in self.modules():
if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
import scipy.stats as stats
stddev = m.stddev if hasattr(m, 'stddev') else 0.1
X = stats.truncnorm(-2, 2, scale=stddev)
values = paddle.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
values = values.view(m.weight.size())
with paddle.no_grad():
m.weight.copy_(values)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)