Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added annotation typing to inception #2857

Merged
merged 8 commits into from
Oct 23, 2020
Merged

Added annotation typing to inception #2857

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
60babcd
style: Added annotation typing for inception
frgfm Oct 21, 2020
c4f8419
refactor: Moved factory function after class definition
frgfm Oct 21, 2020
86ac382
style: Changed attribute setting for type hinting
frgfm Oct 21, 2020
064f948
refactor: Removed un-necessary import
frgfm Oct 22, 2020
70abb17
fix: Fixed typing in constructors
frgfm Oct 22, 2020
372383e
fix: Fixed kwargs typing
frgfm Oct 22, 2020
bcc7547
style: Fixed lint
frgfm Oct 22, 2020
6887ebb
refactor: Moved helpers function back and quote typed it
frgfm Oct 23, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
96 changes: 67 additions & 29 deletions torchvision/models/inception.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.jit.annotations import Optional
from torch import Tensor
from .utils import load_state_dict_from_url
from typing import Callable, Any, Optional, Tuple, List


__all__ = ['Inception3', 'inception_v3', 'InceptionOutputs', '_InceptionOutputs']
Expand All @@ -24,7 +24,7 @@
_InceptionOutputs = InceptionOutputs


def inception_v3(pretrained=False, progress=True, **kwargs):
frgfm marked this conversation as resolved.
Show resolved Hide resolved
def inception_v3(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> "Inception3":
r"""Inception v3 model architecture from
`"Rethinking the Inception Architecture for Computer Vision" <http://arxiv.org/abs/1512.00567>`_.

Expand Down Expand Up @@ -63,8 +63,14 @@ def inception_v3(pretrained=False, progress=True, **kwargs):

class Inception3(nn.Module):

def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
inception_blocks=None, init_weights=None):
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 = [
Expand Down Expand Up @@ -124,15 +130,15 @@ def __init__(self, num_classes=1000, aux_logits=True, transform_input=False,
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)

def _transform_input(self, x):
def _transform_input(self, x: Tensor) -> Tensor:
if self.transform_input:
x_ch0 = torch.unsqueeze(x[:, 0], 1) * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
x_ch1 = torch.unsqueeze(x[:, 1], 1) * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
x_ch2 = torch.unsqueeze(x[:, 2], 1) * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
x = torch.cat((x_ch0, x_ch1, x_ch2), 1)
return x

def _forward(self, x):
def _forward(self, x: Tensor) -> Tuple[Tensor, Optional[Tensor]]:
# N x 3 x 299 x 299
x = self.Conv2d_1a_3x3(x)
# N x 32 x 149 x 149
Expand Down Expand Up @@ -188,13 +194,13 @@ def _forward(self, x):
return x, aux

@torch.jit.unused
def eager_outputs(self, x: torch.Tensor, aux: Optional[Tensor]) -> InceptionOutputs:
def eager_outputs(self, x: Tensor, aux: Optional[Tensor]) -> InceptionOutputs:
if self.training and self.aux_logits:
return InceptionOutputs(x, aux)
else:
return x # type: ignore[return-value]

def forward(self, x):
def forward(self, x: Tensor) -> InceptionOutputs:
x = self._transform_input(x)
x, aux = self._forward(x)
aux_defined = self.training and self.aux_logits
Expand All @@ -208,7 +214,12 @@ def forward(self, x):

class InceptionA(nn.Module):

def __init__(self, in_channels, pool_features, conv_block=None):
def __init__(
self,
in_channels: int,
pool_features: int,
conv_block: Optional[Callable[..., nn.Module]] = None
) -> None:
super(InceptionA, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
Expand All @@ -223,7 +234,7 @@ def __init__(self, in_channels, pool_features, conv_block=None):

self.branch_pool = conv_block(in_channels, pool_features, kernel_size=1)

def _forward(self, x):
def _forward(self, x: Tensor) -> List[Tensor]:
branch1x1 = self.branch1x1(x)

branch5x5 = self.branch5x5_1(x)
Expand All @@ -239,14 +250,18 @@ def _forward(self, x):
outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
return outputs

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
outputs = self._forward(x)
return torch.cat(outputs, 1)


class InceptionB(nn.Module):

def __init__(self, in_channels, conv_block=None):
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
Expand All @@ -256,7 +271,7 @@ def __init__(self, in_channels, conv_block=None):
self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, stride=2)

def _forward(self, x):
def _forward(self, x: Tensor) -> List[Tensor]:
branch3x3 = self.branch3x3(x)

branch3x3dbl = self.branch3x3dbl_1(x)
Expand All @@ -268,14 +283,19 @@ def _forward(self, x):
outputs = [branch3x3, branch3x3dbl, branch_pool]
return outputs

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
outputs = self._forward(x)
return torch.cat(outputs, 1)


class InceptionC(nn.Module):

def __init__(self, in_channels, channels_7x7, conv_block=None):
def __init__(
self,
in_channels: int,
channels_7x7: int,
conv_block: Optional[Callable[..., nn.Module]] = None
) -> None:
super(InceptionC, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
Expand All @@ -294,7 +314,7 @@ def __init__(self, in_channels, channels_7x7, conv_block=None):

self.branch_pool = conv_block(in_channels, 192, kernel_size=1)

def _forward(self, x):
def _forward(self, x: Tensor) -> List[Tensor]:
branch1x1 = self.branch1x1(x)

branch7x7 = self.branch7x7_1(x)
Expand All @@ -313,14 +333,18 @@ def _forward(self, x):
outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
return outputs

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
outputs = self._forward(x)
return torch.cat(outputs, 1)


class InceptionD(nn.Module):

def __init__(self, in_channels, conv_block=None):
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
Expand All @@ -332,7 +356,7 @@ def __init__(self, in_channels, conv_block=None):
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)

def _forward(self, x):
def _forward(self, x: Tensor) -> List[Tensor]:
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)

Expand All @@ -345,14 +369,18 @@ def _forward(self, x):
outputs = [branch3x3, branch7x7x3, branch_pool]
return outputs

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
outputs = self._forward(x)
return torch.cat(outputs, 1)


class InceptionE(nn.Module):

def __init__(self, in_channels, conv_block=None):
def __init__(
self,
in_channels: int,
conv_block: Optional[Callable[..., nn.Module]] = None
) -> None:
super(InceptionE, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
Expand All @@ -369,7 +397,7 @@ def __init__(self, in_channels, conv_block=None):

self.branch_pool = conv_block(in_channels, 192, kernel_size=1)

def _forward(self, x):
def _forward(self, x: Tensor) -> List[Tensor]:
branch1x1 = self.branch1x1(x)

branch3x3 = self.branch3x3_1(x)
Expand All @@ -393,24 +421,29 @@ def _forward(self, x):
outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
return outputs

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
outputs = self._forward(x)
return torch.cat(outputs, 1)


class InceptionAux(nn.Module):

def __init__(self, in_channels, num_classes, conv_block=None):
def __init__(
self,
in_channels: int,
num_classes: int,
conv_block: Optional[Callable[..., nn.Module]] = None
) -> None:
super(InceptionAux, self).__init__()
if conv_block is None:
conv_block = BasicConv2d
self.conv0 = conv_block(in_channels, 128, kernel_size=1)
self.conv1 = conv_block(128, 768, kernel_size=5)
self.conv1.stddev = 0.01
self.conv1.stddev = 0.01 # type: ignore[assignment]
self.fc = nn.Linear(768, num_classes)
self.fc.stddev = 0.001
self.fc.stddev = 0.001 # type: ignore[assignment]

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
# N x 768 x 17 x 17
x = F.avg_pool2d(x, kernel_size=5, stride=3)
# N x 768 x 5 x 5
Expand All @@ -430,12 +463,17 @@ def forward(self, x):

class BasicConv2d(nn.Module):

def __init__(self, in_channels, out_channels, **kwargs):
def __init__(
self,
in_channels: int,
out_channels: int,
**kwargs: Any
) -> None:
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels, eps=0.001)

def forward(self, x):
def forward(self, x: Tensor) -> Tensor:
x = self.conv(x)
x = self.bn(x)
return F.relu(x, inplace=True)