Quantizable googlenet, inceptionv3 and shufflenetv2 models (pytorch#1503)

* quantizable googlenet * Minor improvements * Rename basic_conv2d with conv_block plus additional fixes * More renamings and fixes * Bugfix * Fix missing import for mypy * Add pretrained weights

Author: hx89

torchvision/models/googlenet.py

@@ -5,7 +5,7 @@
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from torch.jit.annotations import Optional
+from torch.jit.annotations import Optional, Tuple
 from torch import Tensor
 from .utils import load_state_dict_from_url
 
@@ -63,34 +63,42 @@ def googlenet(pretrained=False, progress=True, **kwargs):
 class GoogLeNet(nn.Module):
  __constants__ = ['aux_logits', 'transform_input']
 
- def __init__(self, num_classes=1000, aux_logits=True, transform_input=False, init_weights=True):
+ def __init__(self, num_classes=1000, aux_logits=True, transform_input=False, init_weights=True,
+ blocks=None):
  super(GoogLeNet, self).__init__()
+ if blocks is None:
+ blocks = [BasicConv2d, Inception, InceptionAux]
+ assert len(blocks) == 3
+ conv_block = blocks[0]
+ inception_block = blocks[1]
+ inception_aux_block = blocks[2]
+
  self.aux_logits = aux_logits
  self.transform_input = transform_input
 
- self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
+ self.conv1 = conv_block(3, 64, kernel_size=7, stride=2, padding=3)
  self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
- self.conv2 = BasicConv2d(64, 64, kernel_size=1)
- self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
+ self.conv2 = conv_block(64, 64, kernel_size=1)
+ self.conv3 = conv_block(64, 192, kernel_size=3, padding=1)
  self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
 
- self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
- self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
+ self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32)
+ self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64)
  self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
 
- self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
- self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
- self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
- self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
- self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
+ self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64)
+ self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64)
+ self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64)
+ self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64)
+ self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128)
  self.maxpool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
 
- self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
- self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
+ self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128)
+ self.inception5b = inception_block(832, 384, 192, 384, 48, 128, 128)
 
  if aux_logits:
- self.aux1 = InceptionAux(512, num_classes)
- self.aux2 = InceptionAux(528, num_classes)
+ self.aux1 = inception_aux_block(512, num_classes)
+ self.aux2 = inception_aux_block(528, num_classes)
 
  self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
  self.dropout = nn.Dropout(0.2)
@@ -112,14 +120,17 @@ def _initialize_weights(self):
  nn.init.constant_(m.weight, 1)
  nn.init.constant_(m.bias, 0)
 
- def forward(self, x):
- # type: (Tensor) -> GoogLeNetOutputs
+ def _transform_input(self, x):
+ # type: (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):
+ # type: (Tensor) -> Tuple[Tensor, Optional[Tensor], Optional[Tensor]]
  # N x 3 x 224 x 224
  x = self.conv1(x)
  # N x 64 x 112 x 112
@@ -173,12 +184,7 @@ def forward(self, x):
  x = self.dropout(x)
  x = self.fc(x)
  # N x 1000 (num_classes)
- if torch.jit.is_scripting():
- if not aux_defined:
- warnings.warn("Scripted GoogleNet always returns GoogleNetOutputs Tuple")
- return GoogLeNetOutputs(x, aux2, aux1)
- else:
- return self.eager_outputs(x, aux2, aux1)
+ return x, aux2, aux1
 
  @torch.jit.unused
  def eager_outputs(self, x, aux2, aux1):
@@ -188,45 +194,65 @@ def eager_outputs(self, x, aux2, aux1):
  else:
  return x
 
+ def forward(self, x):
+ # type: (Tensor) -> GoogLeNetOutputs
+ x = self._transform_input(x)
+ x, aux1, aux2 = self._forward(x)
+ aux_defined = self.training and self.aux_logits
+ if torch.jit.is_scripting():
+ if not aux_defined:
+ warnings.warn("Scripted GoogleNet always returns GoogleNetOutputs Tuple")
+ return GoogLeNetOutputs(x, aux2, aux1)
+ else:
+ return self.eager_outputs(x, aux2, aux1)
+
 
 class Inception(nn.Module):
  __constants__ = ['branch2', 'branch3', 'branch4']
 
- def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
+ def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj,
+ conv_block=None):
  super(Inception, self).__init__()
-
- self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
+ if conv_block is None:
+ conv_block = BasicConv2d
+ self.branch1 = conv_block(in_channels, ch1x1, kernel_size=1)
 
  self.branch2 = nn.Sequential(
- BasicConv2d(in_channels, ch3x3red, kernel_size=1),
- BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1)
+ conv_block(in_channels, ch3x3red, kernel_size=1),
+ conv_block(ch3x3red, ch3x3, kernel_size=3, padding=1)
  )
 
  self.branch3 = nn.Sequential(
- BasicConv2d(in_channels, ch5x5red, kernel_size=1),
- BasicConv2d(ch5x5red, ch5x5, kernel_size=3, padding=1)
+ conv_block(in_channels, ch5x5red, kernel_size=1),
+ conv_block(ch5x5red, ch5x5, kernel_size=3, padding=1)
  )
 
  self.branch4 = nn.Sequential(
  nn.MaxPool2d(kernel_size=3, stride=1, padding=1, ceil_mode=True),
- BasicConv2d(in_channels, pool_proj, kernel_size=1)
+ conv_block(in_channels, pool_proj, kernel_size=1)
  )
 
- def forward(self, x):
+ def _forward(self, x):
  branch1 = self.branch1(x)
  branch2 = self.branch2(x)
  branch3 = self.branch3(x)
  branch4 = self.branch4(x)
 
  outputs = [branch1, branch2, branch3, branch4]
+ return outputs
+
+ def forward(self, x):
+ outputs = self._forward(x)
  return torch.cat(outputs, 1)
 
 
 class InceptionAux(nn.Module):
 
- def __init__(self, in_channels, num_classes):
+ def __init__(self, in_channels, num_classes, conv_block=None):
  super(InceptionAux, self).__init__()
- self.conv = BasicConv2d(in_channels, 128, kernel_size=1)
+ if conv_block is None:
+ conv_block = BasicConv2d
+ self.conv = conv_block(in_channels, 128, kernel_size=1)
 
  self.fc1 = nn.Linear(2048, 1024)
  self.fc2 = nn.Linear(1024, num_classes)