tst = xse_resnext18()
x = torch.randn(64, 3, 128, 128)
y = tst(x)XResnet
Resnet from bags of tricks paper
init_cnn
def init_cnn(
m
):
XResNet
def XResNet(
block, expansion, layers, p:float=0.0, c_in:int=3, n_out:int=1000, stem_szs:tuple=(32, 32, 64), widen:float=1.0,
sa:bool=False, act_cls:type=ReLU, ndim:int=2, ks:int=3, stride:int=2, groups:int=1, reduction:NoneType=None,
nh1:NoneType=None, nh2:NoneType=None, dw:bool=False, g2:int=1, sym:bool=False,
norm_type:NormType=<NormType.Batch: 1>, pool:function=AvgPool, pool_first:bool=True, padding:NoneType=None,
bias:NoneType=None, bn_1st:bool=True, transpose:bool=False, init:str='auto', xtra:NoneType=None,
bias_std:float=0.01, dilation:Union=1, padding_mode:Literal='zeros', device:NoneType=None, dtype:NoneType=None
):
A sequential container.
Modules will be added to it in the order they are passed in the constructor. Alternatively, an OrderedDict of modules can be passed in. The forward() method of Sequential accepts any input and forwards it to the first module it contains. It then “chains” outputs to inputs sequentially for each subsequent module, finally returning the output of the last module.
The value a Sequential provides over manually calling a sequence of modules is that it allows treating the whole container as a single module, such that performing a transformation on the Sequential applies to each of the modules it stores (which are each a registered submodule of the Sequential).
What’s the difference between a Sequential and a :class:torch.nn.ModuleList? A ModuleList is exactly what it sounds like–a list for storing [Module](https://docs.fast.ai/torch_core.html#module) s! On the other hand, the layers in a Sequential are connected in a cascading way.
Example::
# Using Sequential to create a small model. When `model` is run,
# input will first be passed to `Conv2d(1,20,5)`. The output of
# `Conv2d(1,20,5)` will be used as the input to the first
# `ReLU`; the output of the first `ReLU` will become the input
# for `Conv2d(20,64,5)`. Finally, the output of
# `Conv2d(20,64,5)` will be used as input to the second `ReLU`
model = nn.Sequential(
nn.Conv2d(1, 20, 5), nn.ReLU(), nn.Conv2d(20, 64, 5), nn.ReLU()
)
# Using Sequential with OrderedDict. This is functionally the
# same as the above code
model = nn.Sequential(
OrderedDict(
[
("conv1", nn.Conv2d(1, 20, 5)),
("relu1", nn.ReLU()),
("conv2", nn.Conv2d(20, 64, 5)),
("relu2", nn.ReLU()),
]
)
)xresnet50_deeper
def xresnet50_deeper(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet34_deeper
def xresnet34_deeper(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet18_deeper
def xresnet18_deeper(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet50_deep
def xresnet50_deep(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet34_deep
def xresnet34_deep(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet18_deep
def xresnet18_deep(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet152
def xresnet152(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet101
def xresnet101(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet50
def xresnet50(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet34
def xresnet34(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnet18
def xresnet18(
pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext50_deeper
def xse_resnext50_deeper(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext34_deeper
def xse_resnext34_deeper(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext18_deeper
def xse_resnext18_deeper(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext50_deep
def xse_resnext50_deep(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext34_deep
def xse_resnext34_deep(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext18_deep
def xse_resnext18_deep(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xsenet154
def xsenet154(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnet152
def xse_resnet152(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnext101
def xresnext101(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext101
def xse_resnext101(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnet101
def xse_resnet101(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnext50
def xresnext50(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext50
def xse_resnext50(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnet50
def xse_resnet50(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnext34
def xresnext34(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext34
def xse_resnext34(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnet34
def xse_resnet34(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xresnext18
def xresnext18(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnext18
def xse_resnext18(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
xse_resnet18
def xse_resnet18(
n_out:int=1000, pretrained:bool=False, kwargs:VAR_KEYWORD
):
tst = xresnext18()
x = torch.randn(64, 3, 128, 128)
y = tst(x)tst = xse_resnet50()
x = torch.randn(8, 3, 64, 64)
y = tst(x)tst = xresnet18(ndim=1, c_in=1, ks=15)
x = torch.randn(64, 1, 128)
y = tst(x)tst = xresnext50(ndim=1, c_in=2, ks=31, stride=4)
x = torch.randn(8, 2, 128)
y = tst(x)tst = xresnet18(ndim=3, c_in=3, ks=3)
x = torch.randn(8, 3, 32, 32, 32)
y = tst(x)