Skip to content

GitLab

Unverified Commit 8263c8a1 authored by F-G Fernandez's avatar F-G Fernandez Committed by GitHub
Browse files

Added annotation typing to inception (#2857) 

* style: Added annotation typing for inception

* refactor: Moved factory function after class definition

* style: Changed attribute setting for type hinting

* refactor: Removed un-necessary import

* fix: Fixed typing in constructors

* fix: Fixed kwargs typing

* style: Fixed lint

* refactor: Moved helpers function back and quote typed it
parent 2ce6b189
Show whitespace changes
Inline Side-by-side
Showing with 67 additions and 29 deletions
torchvision/models/inception.py
View file @ 8263c8a1
......@@ -3,9 +3,9 @@ import warnings
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']
......@@ -24,7 +24,7 @@ InceptionOutputs.__annotations__ = {'logits': torch.Tensor, 'aux_logits': Option
_InceptionOutputs = InceptionOutputs
def inception_v3(pretrained=False, progress=True, **kwargs):
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>`_.
......@@ -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 = [
......@@ -124,7 +130,7 @@ class Inception3(nn.Module):
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
......@@ -132,7 +138,7 @@ class Inception3(nn.Module):
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
......@@ -188,13 +194,13 @@ class Inception3(nn.Module):
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
......@@ -208,7 +214,12 @@ class Inception3(nn.Module):
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
......@@ -223,7 +234,7 @@ class InceptionA(nn.Module):
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)
......@@ -239,14 +250,18 @@ class InceptionA(nn.Module):
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
......@@ -256,7 +271,7 @@ class InceptionB(nn.Module):
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)
......@@ -268,14 +283,19 @@ class InceptionB(nn.Module):
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
......@@ -294,7 +314,7 @@ class InceptionC(nn.Module):
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)
......@@ -313,14 +333,18 @@ class InceptionC(nn.Module):
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
......@@ -332,7 +356,7 @@ class InceptionD(nn.Module):
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)
......@@ -345,14 +369,18 @@ class InceptionD(nn.Module):
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
......@@ -369,7 +397,7 @@ class InceptionE(nn.Module):
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)
......@@ -393,24 +421,29 @@ class InceptionE(nn.Module):
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
......@@ -430,12 +463,17 @@ class InceptionAux(nn.Module):
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)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment