def __init__(self, channels):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
self.bn1 = nn.BatchNorm2d(channels)
self.prelu = nn.PReLU()
self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
self.bn2 = nn.BatchNorm2d(channels)
def __init__(
self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1,
):
super(IBasicBlock, self).__init__()
if groups != 1 or base_width != 64:
raise ValueError(
"BasicBlock only supports groups=1 and base_width=64")
if dilation > 1:
raise NotImplementedError(
"Dilation > 1 not supported in BasicBlock")
self.bn1 = nn.BatchNorm2d(
inplanes,
eps=1e-05,
)
self.conv1 = conv3x3(inplanes, planes)
self.bn2 = nn.BatchNorm2d(
planes,
eps=1e-05,
)
self.prelu = nn.ReLU(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn3 = nn.BatchNorm2d(
planes,
eps=1e-05,
)
self.downsample = downsample
self.stride = stride
def __init__(self, in_planes, out_planes, stride, groups):
super(Bottleneck, self).__init__()
self.stride = stride
mid_planes = out_planes // 4
g = 1 if in_planes == 24 else groups
self.conv1 = nn.Conv2d(in_planes,
mid_planes,
kernel_size=1,
groups=g,
bias=False)
self.bn1 = nn.BatchNorm2d(mid_planes)
self.shuffle1 = ShuffleBlock(groups=g)
self.conv2 = nn.Conv2d(mid_planes,
mid_planes,
kernel_size=3,
stride=stride,
padding=1,
groups=mid_planes,
bias=False)
self.bn2 = nn.BatchNorm2d(mid_planes)
self.conv3 = nn.Conv2d(mid_planes,
out_planes,
kernel_size=1,
groups=groups,
bias=False)
self.bn3 = nn.BatchNorm2d(out_planes)
self.shortcut = nn.Sequential()
if stride == 2:
self.shortcut = nn.Sequential(nn.AvgPool2d(3, stride=2, padding=1))
def __init__(self, w_in, w_out, stride, group_width, bottleneck_ratio,
se_ratio):
super(Block, self).__init__()
# 1x1
w_b = int(round(w_out * bottleneck_ratio))
self.conv1 = nn.Conv2d(w_in, w_b, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(w_b)
# 3x3
num_groups = w_b // group_width
self.conv2 = nn.Conv2d(w_b,
w_b,
kernel_size=3,
stride=stride,
padding=1,
groups=num_groups,
bias=False)
self.bn2 = nn.BatchNorm2d(w_b)
# se
self.with_se = se_ratio > 0
if self.with_se:
w_se = int(round(w_in * se_ratio))
self.se = SE(w_b, w_se)
# 1x1
self.conv3 = nn.Conv2d(w_b, w_out, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(w_out)
self.shortcut = nn.Sequential()
if stride != 1 or w_in != w_out:
self.shortcut = nn.Sequential(
nn.Conv2d(w_in,
w_out,
kernel_size=1,
stride=stride,
bias=False), nn.BatchNorm2d(w_out))
def __init__(self, in_planes, out_planes, stride=1):
super(CellB, self).__init__()
self.stride = stride
# Left branch
self.sep_conv1 = SepConv(in_planes,
out_planes,
kernel_size=7,
stride=stride)
self.sep_conv2 = SepConv(in_planes,
out_planes,
kernel_size=3,
stride=stride)
# Right branch
self.sep_conv3 = SepConv(in_planes,
out_planes,
kernel_size=5,
stride=stride)
if stride == 2:
self.conv1 = nn.Conv2d(in_planes,
out_planes,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn1 = nn.BatchNorm2d(out_planes)
# Reduce channels
self.conv2 = nn.Conv2d(2 * out_planes,
out_planes,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn2 = nn.BatchNorm2d(out_planes)
def __init__(self,
in_ch,
out_ch,
kernel_size,
stride,
expansion_factor,
bn_momentum=0.1):
super(_InvertedResidual, self).__init__()
assert stride in [1, 2]
assert kernel_size in [3, 5]
mid_ch = in_ch * expansion_factor
self.apply_resudual = in_ch == out_ch and stride == 1
self.layers = nn.Sequential(
# Pointwise
nn.Conv2d(in_ch, mid_ch, 1, bias=False),
nn.BatchNorm2d(mid_ch, momentum=bn_momentum),
nn.ReLU(inplace=True),
# Depthwise
nn.Conv2d(
mid_ch,
mid_ch,
kernel_size,
padding=kernel_size // 2,
stride=stride,
groups=mid_ch,
bias=False,
),
nn.BatchNorm2d(mid_ch, momentum=bn_momentum),
nn.ReLU(inplace=True),
# Linear pointwise, Note that there's no activation
nn.Conv2d(mid_ch, out_ch, 1, bias=False),
nn.BatchNorm2d(out_ch, momentum=bn_momentum),
)
def __init__(self, inp: int, oup: int, stride: int) -> None:
super().__init__()
if not (1 <= stride <= 3):
raise ValueError("illegal stride value")
self.stride = stride
branch_features = oup // 2
assert (self.stride != 1) or (inp == branch_features << 1)
if self.stride > 1:
self.branch1 = nn.Sequential(
self.depthwise_conv(inp,
inp,
kernel_size=3,
stride=self.stride,
padding=1),
nn.BatchNorm2d(inp),
nn.Conv2d(inp,
branch_features,
kernel_size=1,
stride=1,
padding=0,
bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
)
else:
self.branch1 = nn.Sequential()
self.branch2 = nn.Sequential(
nn.Conv2d(
inp if (self.stride > 1) else branch_features,
branch_features,
kernel_size=1,
stride=1,
padding=0,
bias=False,
),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
self.depthwise_conv(
branch_features,
branch_features,
kernel_size=3,
stride=self.stride,
padding=1,
),
nn.BatchNorm2d(branch_features),
nn.Conv2d(
branch_features,
branch_features,
kernel_size=1,
stride=1,
padding=0,
bias=False,
),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
)
def __init__(self, block=BasicBlock, num_classes=10):
super(DLA, self).__init__()
self.base = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1, bias=False),
nn.BatchNorm2d(16),
nn.ReLU(True)
)
self.layer1 = nn.Sequential(
nn.Conv2d(16, 16, kernel_size=3, stride=1, padding=1, bias=False),
nn.BatchNorm2d(16),
nn.ReLU(True)
)
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1, bias=False),
nn.BatchNorm2d(32),
nn.ReLU(True)
)
self.layer3 = Tree(block, 32, 64, level=1, stride=1)
self.layer4 = Tree(block, 64, 128, level=2, stride=2)
self.layer5 = Tree(block, 128, 256, level=2, stride=2)
self.layer6 = Tree(block, 256, 512, level=1, stride=2)
self.linear = nn.Linear(512, num_classes)
def __init__(self, in_planes, planes, stride=1):
super(PreActBlock, self).__init__()
self.bn1 = nn.BatchNorm2d(in_planes)
self.conv1 = nn.Conv2d(in_planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes,
planes,
kernel_size=3,
stride=1,
padding=1,
bias=False)
if stride != 1 or in_planes != planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes,
planes,
kernel_size=1,
stride=stride,
bias=False))
# SE layers
self.fc1 = nn.Conv2d(planes, planes // 16, kernel_size=1)
self.fc2 = nn.Conv2d(planes // 16, planes, kernel_size=1)
def __init__(self, last_planes, in_planes, out_planes, dense_depth, stride,
first_layer):
super(Bottleneck, self).__init__()
self.out_planes = out_planes
self.dense_depth = dense_depth
self.conv1 = nn.Conv2d(last_planes,
in_planes,
kernel_size=1,
bias=False)
self.bn1 = nn.BatchNorm2d(in_planes)
self.conv2 = nn.Conv2d(in_planes,
in_planes,
kernel_size=3,
stride=stride,
padding=1,
groups=32,
bias=False)
self.bn2 = nn.BatchNorm2d(in_planes)
self.conv3 = nn.Conv2d(in_planes,
out_planes + dense_depth,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(out_planes + dense_depth)
self.shortcut = nn.Sequential()
if first_layer:
self.shortcut = nn.Sequential(
nn.Conv2d(last_planes,
out_planes + dense_depth,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(out_planes + dense_depth))
def __init__(self, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes,
planes,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes,
self.expansion * planes,
kernel_size=1,
stride=stride,
bias=False), nn.BatchNorm2d(self.expansion * planes))
def __init__(self,
in_planes,
cardinality=32,
bottleneck_width=4,
stride=1):
super(Block, self).__init__()
group_width = cardinality * bottleneck_width
self.conv1 = nn.Conv2d(in_planes,
group_width,
kernel_size=1,
bias=False)
self.bn1 = nn.BatchNorm2d(group_width)
self.conv2 = nn.Conv2d(group_width,
group_width,
kernel_size=3,
stride=stride,
padding=1,
groups=cardinality,
bias=False)
self.bn2 = nn.BatchNorm2d(group_width)
self.conv3 = nn.Conv2d(group_width,
self.expansion * group_width,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion * group_width)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * group_width:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes,
self.expansion * group_width,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(self.expansion * group_width))
def __init__(
self,
in_chs,
mid_chs,
out_chs,
dw_kernel_size=3,
stride=1,
act_layer=nn.ReLU,
se_ratio=0.0,
):
super(GhostBottleneck, self).__init__()
has_se = se_ratio is not None and se_ratio > 0.0
self.stride = stride
# Point-wise expansion
self.ghost1 = GhostModule(in_chs, mid_chs, relu=True)
# Depth-wise convolution
if self.stride > 1:
self.conv_dw = nn.Conv2d(
mid_chs,
mid_chs,
dw_kernel_size,
stride=stride,
padding=(dw_kernel_size - 1) // 2,
groups=mid_chs,
bias=False,
)
self.bn_dw = nn.BatchNorm2d(mid_chs)
# Squeeze-and-excitation
if has_se:
self.se = SqueezeExcite(mid_chs, se_ratio=se_ratio)
else:
self.se = None
# Point-wise linear projection
self.ghost2 = GhostModule(mid_chs, out_chs, relu=False)
# shortcut
if in_chs == out_chs and self.stride == 1:
self.shortcut = nn.Sequential()
else:
self.shortcut = nn.Sequential(
nn.Conv2d(
in_chs,
in_chs,
dw_kernel_size,
stride=stride,
padding=(dw_kernel_size - 1) // 2,
groups=in_chs,
bias=False,
),
nn.BatchNorm2d(in_chs),
nn.Conv2d(in_chs, out_chs, 1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(out_chs),
)
def __init__(self, in_channels, out_channels):
super().__init__()
self.double_conv = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
)
def __init__(self, in_planes, growth_rate):
super(Bottleneck, self).__init__()
self.bn1 = nn.BatchNorm2d(in_planes)
self.conv1 = nn.Conv2d(in_planes,
4 * growth_rate,
kernel_size=1,
bias=False)
self.bn2 = nn.BatchNorm2d(4 * growth_rate)
self.conv2 = nn.Conv2d(4 * growth_rate,
growth_rate,
kernel_size=3,
padding=1,
bias=False)
def __init__(
self,
stages_repeats: List[int],
stages_out_channels: List[int],
num_classes: int = 1000,
inverted_residual: Callable[..., nn.Module] = InvertedResidual,
) -> None:
super().__init__()
if len(stages_repeats) != 3:
raise ValueError(
"expected stages_repeats as list of 3 positive ints")
if len(stages_out_channels) != 5:
raise ValueError(
"expected stages_out_channels as list of 5 positive ints")
self._stage_out_channels = stages_out_channels
input_channels = 3
output_channels = self._stage_out_channels[0]
self.conv1 = nn.Sequential(
nn.Conv2d(input_channels, output_channels, 3, 2, 1, bias=False),
nn.BatchNorm2d(output_channels),
nn.ReLU(inplace=True),
)
input_channels = output_channels
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
# Static annotations for mypy
self.stage2: nn.Sequential
self.stage3: nn.Sequential
self.stage4: nn.Sequential
stage_names = ["stage{}".format(i) for i in [2, 3, 4]]
for name, repeats, output_channels in zip(
stage_names, stages_repeats, self._stage_out_channels[1:]):
seq = [inverted_residual(input_channels, output_channels, 2)]
for i in range(repeats - 1):
seq.append(
inverted_residual(output_channels, output_channels, 1))
setattr(self, name, nn.Sequential(*seq))
input_channels = output_channels
output_channels = self._stage_out_channels[-1]
self.conv5 = nn.Sequential(
nn.Conv2d(input_channels, output_channels, 1, 1, 0, bias=False),
nn.BatchNorm2d(output_channels),
nn.ReLU(inplace=True),
)
self.fc = nn.Linear(output_channels, num_classes)
def __init__(self,
in_channels,
out_channels,
kernel_size,
stride,
expand_ratio=1,
se_ratio=0.,
drop_rate=0.):
super(Block, self).__init__()
self.stride = stride
self.drop_rate = drop_rate
self.expand_ratio = expand_ratio
# Expansion
channels = expand_ratio * in_channels
self.conv1 = nn.Conv2d(in_channels,
channels,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn1 = nn.BatchNorm2d(channels)
# Depthwise conv
self.conv2 = nn.Conv2d(channels,
channels,
kernel_size=kernel_size,
stride=stride,
padding=(1 if kernel_size == 3 else 2),
groups=channels,
bias=False)
self.bn2 = nn.BatchNorm2d(channels)
# SE layers
se_channels = int(in_channels * se_ratio)
self.se = SE(channels, se_channels)
# Output
self.conv3 = nn.Conv2d(channels,
out_channels,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn3 = nn.BatchNorm2d(out_channels)
# Skip connection if in and out shapes are the same (MV-V2 style)
self.has_skip = (stride == 1) and (in_channels == out_channels)
def __init__(self, cfg):
super(DPN, self).__init__()
in_planes, out_planes = cfg['in_planes'], cfg['out_planes']
num_blocks, dense_depth = cfg['num_blocks'], cfg['dense_depth']
self.conv1 = nn.Conv2d(3,
64,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.last_planes = 64
self.layer1 = self._make_layer(in_planes[0],
out_planes[0],
num_blocks[0],
dense_depth[0],
stride=1)
self.layer2 = self._make_layer(in_planes[1],
out_planes[1],
num_blocks[1],
dense_depth[1],
stride=2)
self.layer3 = self._make_layer(in_planes[2],
out_planes[2],
num_blocks[2],
dense_depth[2],
stride=2)
self.layer4 = self._make_layer(in_planes[3],
out_planes[3],
num_blocks[3],
dense_depth[3],
stride=2)
self.linear = nn.Linear(
out_planes[3] + (num_blocks[3] + 1) * dense_depth[3], 10)
def __init__(self, in_planes, out_planes, stride=1):
super(Block, self).__init__()
self.conv1 = nn.Conv2d(in_planes,
in_planes,
kernel_size=3,
stride=stride,
padding=1,
groups=in_planes,
bias=False)
self.bn1 = nn.BatchNorm2d(in_planes)
self.conv2 = nn.Conv2d(in_planes,
out_planes,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn2 = nn.BatchNorm2d(out_planes)
def __init__(self):
super(Discriminator, self).__init__()
self.net = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, padding=1),
nn.LeakyReLU(0.2),
nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(64),
nn.LeakyReLU(0.2),
nn.Conv2d(64, 128, kernel_size=3, padding=1),
nn.BatchNorm2d(128),
nn.LeakyReLU(0.2),
nn.Conv2d(128, 128, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(128),
nn.LeakyReLU(0.2),
nn.Conv2d(128, 256, kernel_size=3, padding=1),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2),
nn.Conv2d(256, 256, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2),
nn.Conv2d(256, 512, kernel_size=3, padding=1),
nn.BatchNorm2d(512),
nn.LeakyReLU(0.2),
nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1),
nn.BatchNorm2d(512),
nn.LeakyReLU(0.2),
nn.AdaptiveAvgPool2d(1),
nn.Conv2d(512, 1024, kernel_size=1),
nn.LeakyReLU(0.2),
nn.Conv2d(1024, 1, kernel_size=1),
)
def __init__(self, in_channels, out_channels, kernel_size=1):
super(Root, self).__init__()
self.conv = nn.Conv2d(in_channels,
out_channels,
kernel_size,
stride=1,
padding=(kernel_size - 1) // 2,
bias=False)
self.bn = nn.BatchNorm2d(out_channels)
def __init__(self, in_planes, out_planes, kernel_size, stride):
super(SepConv, self).__init__()
self.conv1 = nn.Conv2d(in_planes,
out_planes,
kernel_size,
stride,
padding=(kernel_size - 1) // 2,
bias=False,
groups=in_planes)
self.bn1 = nn.BatchNorm2d(out_planes)
def __init__(self, num_classes=10):
super(MobileNetV2, self).__init__()
# NOTE: change conv1 stride 2 -> 1 for CIFAR10
self.conv1 = nn.Conv2d(3,
32,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(32)
self.layers = self._make_layers(in_planes=32)
self.conv2 = nn.Conv2d(320,
1280,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn2 = nn.BatchNorm2d(1280)
self.linear = nn.Linear(1280, num_classes)
def __init__(self, alpha, num_classes=1000, dropout=0.2):
super(MNASNet, self).__init__()
assert alpha > 0.0
self.alpha = alpha
self.num_classes = num_classes
depths = _get_depths(alpha)
layers = [
# First layer: regular conv.
nn.Conv2d(3, depths[0], 3, padding=1, stride=2, bias=False),
nn.BatchNorm2d(depths[0], momentum=_BN_MOMENTUM),
nn.ReLU(inplace=True),
# Depthwise separable, no skip.
nn.Conv2d(
depths[0],
depths[0],
3,
padding=1,
stride=1,
groups=depths[0],
bias=False,
),
nn.BatchNorm2d(depths[0], momentum=_BN_MOMENTUM),
nn.ReLU(inplace=True),
nn.Conv2d(depths[0], depths[1], 1, padding=0, stride=1,
bias=False),
nn.BatchNorm2d(depths[1], momentum=_BN_MOMENTUM),
# MNASNet blocks: stacks of inverted residuals.
_stack(depths[1], depths[2], 3, 2, 3, 3, _BN_MOMENTUM),
_stack(depths[2], depths[3], 5, 2, 3, 3, _BN_MOMENTUM),
_stack(depths[3], depths[4], 5, 2, 6, 3, _BN_MOMENTUM),
_stack(depths[4], depths[5], 3, 1, 6, 2, _BN_MOMENTUM),
_stack(depths[5], depths[6], 5, 2, 6, 4, _BN_MOMENTUM),
_stack(depths[6], depths[7], 3, 1, 6, 1, _BN_MOMENTUM),
# Final mapping to classifier input.
nn.Conv2d(depths[7], 1280, 1, padding=0, stride=1, bias=False),
nn.BatchNorm2d(1280, momentum=_BN_MOMENTUM),
nn.ReLU(inplace=True),
]
self.layers = nn.Sequential(*layers)
self.classifier = nn.Sequential(nn.Dropout(p=dropout, inplace=True),
nn.Linear(1280, num_classes))
self._initialize_weights()
def __init__(self, num_classes=10):
super(MobileNet, self).__init__()
self.conv1 = nn.Conv2d(3,
32,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(32)
self.layers = self._make_layers(in_planes=32)
self.linear = nn.Linear(1024, num_classes)
def __init__(self, cfg, num_classes=10):
super(EfficientNet, self).__init__()
self.cfg = cfg
self.conv1 = nn.Conv2d(3,
32,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(32)
self.layers = self._make_layers(in_channels=32)
self.linear = nn.Linear(cfg['out_channels'][-1], num_classes)
def __init__(self, in_channels, n_filters) -> None:
super().__init__()
self.relu = nn.ReLU(inplace=True)
self.conv1 = nn.Conv2d(in_channels, in_channels // 4, 1)
self.norm1 = nn.BatchNorm2d(in_channels // 4)
self.deconv2 = nn.ConvTranspose2d(
in_channels // 4,
in_channels // 4,
kernel_size=4,
stride=2,
padding=1,
output_padding=0,
)
self.norm2 = nn.BatchNorm2d(in_channels // 4)
self.conv3 = nn.Conv2d(in_channels // 4, n_filters, 1)
self.norm3 = nn.BatchNorm2d(n_filters)
def __init__(
self,
num_input_features: int,
growth_rate: int,
bn_size: int,
drop_rate: float,
) -> None:
super(_DenseLayer, self).__init__()
self.norm1: nn.BatchNorm2d
self.add_module("norm1", nn.BatchNorm2d(num_input_features))
self.relu1: nn.ReLU
self.add_module("relu1", nn.ReLU(inplace=True))
self.conv1: nn.Conv2d
self.add_module(
"conv1",
nn.Conv2d(
num_input_features,
bn_size * growth_rate,
kernel_size=1,
stride=1,
bias=False,
),
)
self.norm2: nn.BatchNorm2d
self.add_module("norm2", nn.BatchNorm2d(bn_size * growth_rate))
self.relu2: nn.ReLU
self.add_module("relu2", nn.ReLU(inplace=True))
self.conv2: nn.Conv2d
self.add_module(
"conv2",
nn.Conv2d(
bn_size * growth_rate,
growth_rate,
kernel_size=3,
stride=1,
padding=1,
bias=False,
),
)
self.drop_rate = float(drop_rate)
def __init__(
self,
input_size,
in_channel,
out_channel,
kernel_size,
stride,
dropout=0.1,
batch_norm=False,
residual=False,
act_func_type="relu",
):
super(Conv2dLayer, self).__init__()
self.input_size = input_size
self.in_channel = in_channel
self.out_channel = out_channel
self.batch_norm = batch_norm
self.kernel_size = kernel_size
self.stride = stride
self.padding = (
0,
kernel_size //
2 if isinstance(self.kernel_size, int) else kernel_size[1] // 2,
)
self.residual = residual
self.act_func_type = act_func_type
self.conv_layer = nn.Conv2d(
in_channels=in_channel,
out_channels=out_channel,
kernel_size=self.kernel_size,
stride=self.stride,
padding=self.padding,
)
self.output_size = cal_width_dim_2d(
input_size,
self.kernel_size
if isinstance(self.kernel_size, int) else self.kernel_size[1],
self.stride if isinstance(self.stride, int) else self.stride[1],
padding=self.padding
if isinstance(self.padding, int) else self.padding[1],
)
if self.batch_norm:
self.norm = nn.BatchNorm2d(out_channel)
self.dropout = nn.Dropout(dropout)
def __init__(self, cfgs, num_classes=1000, width=1.0, dropout=0.2):
super(GhostNet, self).__init__()
# setting of inverted residual blocks
self.cfgs = cfgs
self.dropout = dropout
# building first layer
output_channel = _make_divisible(16 * width, 4)
self.conv_stem = nn.Conv2d(3, output_channel, 3, 2, 1, bias=False)
self.bn1 = nn.BatchNorm2d(output_channel)
self.act1 = nn.ReLU(inplace=True)
input_channel = output_channel
# building inverted residual blocks
stages = []
block = GhostBottleneck
for cfg in self.cfgs:
layers = []
for k, exp_size, c, se_ratio, s in cfg:
output_channel = _make_divisible(c * width, 4)
hidden_channel = _make_divisible(exp_size * width, 4)
layers.append(
block(
input_channel,
hidden_channel,
output_channel,
k,
s,
se_ratio=se_ratio,
))
input_channel = output_channel
stages.append(nn.Sequential(*layers))
output_channel = _make_divisible(exp_size * width, 4)
stages.append(
nn.Sequential(ConvBnAct(input_channel, output_channel, 1)))
input_channel = output_channel
self.blocks = nn.Sequential(*stages)
# building last several layers
output_channel = 1280
self.global_pool = nn.AdaptiveAvgPool2d((1, 1))
self.conv_head = nn.Conv2d(input_channel,
output_channel,
1,
1,
0,
bias=True)
self.act2 = nn.ReLU(inplace=True)
self.classifier = nn.Linear(output_channel, num_classes)
self.dropout = nn.Dropout(p=self.dropout)
