def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def __init__(self):
super(ModuleDict, self).__init__()
self.choices = nn.ModuleDict(
{"conv": nn.Conv2d(10, 10, 3), "pool": nn.MaxPool2d(3)}
)
self.activations = nn.ModuleDict(
{"relu": nn.ReLU(), "prelu": nn.PReLU()}
)
def __init__(self):
super(LeNet, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(1, 6,
kernel_size=5), # in_channels, out_channels, kernel_size
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2), # kernel_size, stride
nn.Conv2d(6, 16, 5),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
)
self.fc = nn.Sequential(
nn.Linear(16 * 4 * 4, 120),
nn.ReLU(),
nn.Linear(120, 84),
nn.ReLU(),
nn.Linear(84, 10),
)
def __init__(
self,
in_channels: int,
conv_block: Optional[Callable[..., nn.Module]] = None) -> None:
super(InceptionB, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch3x3 = conv_block(in_channels, 384, kernel_size=3, stride=2)
self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, stride=2)
self.max_pool = nn.MaxPool2d(kernel_size=3, stride=2)
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, input_channels):
super().__init__()
self.Branch_2 = nn.MaxPool2d(3, stride=2)
self.Branch_0 = nn.Sequential(
BasicConv2d(input_channels, 384, kernel_size=3, stride=2)
)
self.Branch_1 = nn.Sequential(
BasicConv2d(input_channels, 256, kernel_size=1),
BasicConv2d(256, 256, kernel_size=3, padding=1),
BasicConv2d(256, 384, kernel_size=3, stride=2),
)
def _make_layers(self, cfg):
layers = []
in_channels = 3
for x in cfg:
if x == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
layers += [
nn.Conv2d(in_channels, x, kernel_size=3, padding=1),
nn.BatchNorm2d(x),
nn.ReLU(inplace=True)
]
in_channels = x
layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
return nn.Sequential(*layers)
def make_layers(cfg: List[Union[str, int]],
batch_norm: bool = False) -> nn.Sequential:
layers: List[nn.Module] = []
in_channels = 3
for v in cfg:
if v == "M":
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
v = cast(int, v)
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)
def __init__(
self,
block: Type[Union[BasicBlock, Bottleneck]],
layers: List[int],
num_classes: int = 1000,
pretrained=None,
groups: int = 1,
width_per_group: int = 64,
replace_stride_with_dilation: Optional[List[bool]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None,
) -> None:
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.pretrained = pretrained
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 = nn.Conv2d(
3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False
)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU()
self.maxpool = nn.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]
)
def _make_level(self, block, inplanes, planes, blocks, stride=1):
downsample = None
if stride != 1 or inplanes != planes:
downsample = nn.Sequential(
nn.MaxPool2d(stride, stride=stride),
nn.Conv2d(inplanes,
planes,
kernel_size=1,
stride=1,
bias=False),
BatchNorm(planes),
)
layers = []
layers.append(block(inplanes, planes, stride, downsample=downsample))
for i in range(1, blocks):
layers.append(block(inplanes, planes))
return nn.Sequential(*layers)
def __init__(
self,
in_channels: int,
conv_block: Optional[Callable[..., nn.Module]] = None) -> None:
super(InceptionD, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.branch3x3_1 = conv_block(in_channels, 192, kernel_size=1)
self.branch3x3_2 = conv_block(192, 320, kernel_size=3, stride=2)
self.branch7x7x3_1 = conv_block(in_channels, 192, kernel_size=1)
self.branch7x7x3_2 = conv_block(192,
192,
kernel_size=(1, 7),
padding=(0, 3))
self.branch7x7x3_3 = conv_block(192,
192,
kernel_size=(7, 1),
padding=(3, 0))
self.branch7x7x3_4 = conv_block(192, 192, kernel_size=3, stride=2)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2)
def make_layers(cfg, in_channels=3, batch_norm=False, dilation=False):
if dilation:
d_rate = 2
else:
d_rate = 1
layers = []
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=d_rate,
dilation=d_rate)
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)
def __init__(self, in_planes, n1x1, n3x3red, n3x3, n5x5red, n5x5,
pool_planes):
super(Inception, self).__init__()
# 1x1 conv branch
self.b1 = nn.Sequential(
nn.Conv2d(in_planes, n1x1, kernel_size=1),
nn.BatchNorm2d(n1x1),
nn.ReLU(True),
)
# 1x1 conv -> 3x3 conv branch
self.b2 = nn.Sequential(
nn.Conv2d(in_planes, n3x3red, kernel_size=1),
nn.BatchNorm2d(n3x3red),
nn.ReLU(True),
nn.Conv2d(n3x3red, n3x3, kernel_size=3, padding=1),
nn.BatchNorm2d(n3x3),
nn.ReLU(True),
)
# 1x1 conv -> 5x5 conv branch
self.b3 = nn.Sequential(
nn.Conv2d(in_planes, n5x5red, kernel_size=1),
nn.BatchNorm2d(n5x5red),
nn.ReLU(True),
nn.Conv2d(n5x5red, n5x5, kernel_size=3, padding=1),
nn.BatchNorm2d(n5x5),
nn.ReLU(True),
nn.Conv2d(n5x5, n5x5, kernel_size=3, padding=1),
nn.BatchNorm2d(n5x5),
nn.ReLU(True),
)
# 3x3 pool -> 1x1 conv branch
self.b4 = nn.Sequential(
nn.MaxPool2d(3, stride=1, padding=1),
nn.Conv2d(in_planes, pool_planes, kernel_size=1),
nn.BatchNorm2d(pool_planes),
nn.ReLU(True),
)
def __init__(self):
super(GoogLeNet, self).__init__()
self.pre_layers = nn.Sequential(
nn.Conv2d(3, 192, kernel_size=3, padding=1),
nn.BatchNorm2d(192),
nn.ReLU(True),
)
self.a3 = Inception(192, 64, 96, 128, 16, 32, 32)
self.b3 = Inception(256, 128, 128, 192, 32, 96, 64)
self.maxpool = nn.MaxPool2d(3, stride=2, padding=1)
self.a4 = Inception(480, 192, 96, 208, 16, 48, 64)
self.b4 = Inception(512, 160, 112, 224, 24, 64, 64)
self.c4 = Inception(512, 128, 128, 256, 24, 64, 64)
self.d4 = Inception(512, 112, 144, 288, 32, 64, 64)
self.e4 = Inception(528, 256, 160, 320, 32, 128, 128)
self.a5 = Inception(832, 256, 160, 320, 32, 128, 128)
self.b5 = Inception(832, 384, 192, 384, 48, 128, 128)
self.avgpool = nn.AvgPool2d(8, stride=1)
self.linear = nn.Linear(1024, 10)
def __init__(
self,
levels,
block,
in_channels,
out_channels,
stride=1,
level_root=False,
root_dim=0,
root_kernel_size=1,
dilation=1,
root_residual=False,
):
super(Tree, self).__init__()
if root_dim == 0:
root_dim = 2 * out_channels
if level_root:
root_dim += in_channels
if levels == 1:
self.tree1 = block(in_channels,
out_channels,
stride,
dilation=dilation)
self.tree2 = block(out_channels,
out_channels,
1,
dilation=dilation)
else:
self.tree1 = Tree(
levels - 1,
block,
in_channels,
out_channels,
stride,
root_dim=0,
root_kernel_size=root_kernel_size,
dilation=dilation,
root_residual=root_residual,
)
self.tree2 = Tree(
levels - 1,
block,
out_channels,
out_channels,
root_dim=root_dim + out_channels,
root_kernel_size=root_kernel_size,
dilation=dilation,
root_residual=root_residual,
)
if levels == 1:
self.root = Root(root_dim, out_channels, root_kernel_size,
root_residual)
self.level_root = level_root
self.root_dim = root_dim
self.downsample = None
self.project = None
self.levels = levels
if stride > 1:
self.downsample = nn.MaxPool2d(stride, stride=stride)
if in_channels != out_channels:
self.project = nn.Sequential(
nn.Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=1,
bias=False),
BatchNorm(out_channels),
)
def __init__(
self,
num_classes: int = 1000,
aux_logits: bool = True,
transform_input: bool = False,
inception_blocks: Optional[List[Callable[..., nn.Module]]] = None,
init_weights: Optional[bool] = None,
) -> 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: Optional[nn.Module] = 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):
stddev = float(m.stddev) if hasattr(
m, "stddev") else 0.1 # type: ignore
flow.nn.init.trunc_normal_(m.weight,
mean=0.0,
std=stddev,
a=-2,
b=2)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def __init__(
self,
block,
layers,
zero_init_residual=False,
groups=1,
width_per_group=64,
replace_stride_with_dilation=None,
norm_layer=None,
last_stride=1,
):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.feature_dim = 512 * block.expansion
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 = nn.Conv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.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=last_stride,
dilate=replace_stride_with_dilation[2],
)
self._init_params()
# 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)
def __init__(self, in_channels, out_channels):
super().__init__()
self.maxpool_conv = nn.Sequential(
nn.MaxPool2d(2), DoubleConv(in_channels, out_channels))
def __init__(
self,
block: Type[Union[BasicBlock, Bottleneck]],
layers: List[int],
num_classes: int = 1000,
zero_init_residual: bool = False,
groups: int = 1,
width_per_group: int = 64,
replace_stride_with_dilation: Optional[List[bool]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None,
) -> None:
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.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 = nn.Conv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU()
self.maxpool = nn.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 = nn.AvgPool2d((7, 7))
self.fc = nn.Linear(512 * block.expansion, num_classes)
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.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) # type: ignore[arg-type]
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight,
0) # type: ignore[arg-type]
def __init__(
self,
block: Type[Union[BasicBlock, Bottleneck]],
layers: List[int],
num_classes: int = 1000,
zero_init_residual: bool = False,
groups: int = 1,
width_per_group: int = 64,
replace_stride_with_dilation: Optional[List[bool]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None,
) -> None:
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
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 = nn.Conv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU()
self.maxpool = nn.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 = nn.AvgPool2d((7, 7))
self.fc = nn.Linear(512 * block.expansion, num_classes)
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.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
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)
def __init__(
self,
growth_rate: int = 32,
block_config: Tuple[int, int, int, int] = (6, 12, 24, 16),
num_init_features: int = 64,
bn_size: int = 4,
drop_rate: float = 0,
num_classes: int = 1000,
) -> None:
super(DenseNet, self).__init__()
# First convolution
self.features = nn.Sequential(
OrderedDict([
(
"conv0",
nn.Conv2d(
3,
num_init_features,
kernel_size=7,
stride=2,
padding=3,
bias=False,
),
),
("norm0", nn.BatchNorm2d(num_init_features)),
("relu0", nn.ReLU(inplace=True)),
("pool0", nn.MaxPool2d(kernel_size=3, stride=2, padding=1)),
]))
# Each denseblock
num_features = num_init_features
for i, num_layers in enumerate(block_config):
block = _DenseBlock(
num_layers=num_layers,
num_input_features=num_features,
bn_size=bn_size,
growth_rate=growth_rate,
drop_rate=drop_rate,
)
self.features.add_module("denseblock%d" % (i + 1), block)
num_features = num_features + num_layers * growth_rate
if i != len(block_config) - 1:
trans = _Transition(
num_input_features=num_features,
num_output_features=num_features // 2,
)
self.features.add_module("transition%d" % (i + 1), trans)
num_features = num_features // 2
# Final batch norm
self.features.add_module("norm5", nn.BatchNorm2d(num_features))
# Linear layer
self.classifier = nn.Linear(num_features, num_classes)
# Official init from torch repo.
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.constant_(m.bias, 0)
def quantize(
self,
quantization_bit=8,
quantization_scheme="symmetric",
quantization_formula="google",
per_layer_quantization=True,
):
self.q_features = nn.Sequential(
q_conv(
self.features[0],
qi=True,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
q_conv(
self.features[3],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
q_conv(
self.features[6],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
q_conv(
self.features[8],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
q_conv(
self.features[10],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.q_avgpool = nn.AdaptiveAvgPool2d((6, 6))
self.q_classifier = nn.Sequential(
nn.Dropout(),
q_linear(
self.classifier[1],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
nn.Dropout(),
q_linear(
self.classifier[4],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
nn.ReLU(inplace=True),
q_linear(
self.classifier[6],
qi=False,
qo=True,
quantization_bit=quantization_bit,
quantization_scheme=quantization_scheme,
quantization_formula=quantization_formula,
per_layer_quantization=per_layer_quantization,
),
)
