[#85]: Xception backbone for Deeplab

VainF · Jul 31, 2022 · c4b51e4 · c4b51e4 · RoaringFlood · Aug 2, 2022
1 parent 1d6fedf
commit c4b51e4
Show file tree

Hide file tree

Showing 4 changed files with 294 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -14,6 +14,7 @@ Specify the model architecture with '--model ARCH_NAME' and set the output strid
 |deeplabv3_mobilenet|deeplabv3plus_mobilenet ||
 |deeplabv3_hrnetv2_48 | deeplabv3plus_hrnetv2_48 |
 |deeplabv3_hrnetv2_32 | deeplabv3plus_hrnetv2_32 |
+|deeplabv3_xception | deeplabv3plus_xception |
 
 All pretrained models: [Dropbox](https://www.dropbox.com/sh/w3z9z8lqpi8b2w7/AAB0vkl4F5vy6HdIhmRCTKHSa?dl=0), [Tencent Weiyun](https://share.weiyun.com/qqx78Pv5)
 

diff --git a/network/backbone/__init__.py b/network/backbone/__init__.py
@@ -1,3 +1,4 @@
 from . import resnet
 from . import mobilenetv2
 from . import hrnetv2
+from . import xception
diff --git a/network/backbone/xception.py b/network/backbone/xception.py
@@ -0,0 +1,238 @@
+
+"""
+Xception is adapted from https://github.com/Cadene/pretrained-models.pytorch/blob/master/pretrainedmodels/models/xception.py
+
+Ported to pytorch thanks to [tstandley](https://github.com/tstandley/Xception-PyTorch)
+@author: tstandley
+Adapted by cadene
+Creates an Xception Model as defined in:
+Francois Chollet
+Xception: Deep Learning with Depthwise Separable Convolutions
+https://arxiv.org/pdf/1610.02357.pdf
+This weights ported from the Keras implementation. Achieves the following performance on the validation set:
+Loss:0.9173 Prec@1:78.892 Prec@5:94.292
+REMEMBER to set your image size to 3x299x299 for both test and validation
+normalize = transforms.Normalize(mean=[0.5, 0.5, 0.5],
+                                  std=[0.5, 0.5, 0.5])
+The resize parameter of the validation transform should be 333, and make sure to center crop at 299x299
+"""
+from __future__ import print_function, division, absolute_import
+import math
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.utils.model_zoo as model_zoo
+from torch.nn import init
+
+__all__ = ['xception']
+
+pretrained_settings = {
+    'xception': {
+        'imagenet': {
+            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/xception-43020ad28.pth',
+            'input_space': 'RGB',
+            'input_size': [3, 299, 299],
+            'input_range': [0, 1],
+            'mean': [0.5, 0.5, 0.5],
+            'std': [0.5, 0.5, 0.5],
+            'num_classes': 1000,
+            'scale': 0.8975 # The resize parameter of the validation transform should be 333, and make sure to center crop at 299x299
+        }
+    }
+}
+
+
+class SeparableConv2d(nn.Module):
+    def __init__(self,in_channels,out_channels,kernel_size=1,stride=1,padding=0,dilation=1,bias=False):
+        super(SeparableConv2d,self).__init__()
+
+        self.conv1 = nn.Conv2d(in_channels,in_channels,kernel_size,stride,padding,dilation,groups=in_channels,bias=bias)
+        self.pointwise = nn.Conv2d(in_channels,out_channels,1,1,0,1,1,bias=bias)
+
+    def forward(self,x):
+        x = self.conv1(x)
+        x = self.pointwise(x)
+        return x
+
+
+class Block(nn.Module):
+    def __init__(self,in_filters,out_filters,reps,strides=1,start_with_relu=True,grow_first=True, dilation=1):
+        super(Block, self).__init__()
+
+        if out_filters != in_filters or strides!=1:
+            self.skip = nn.Conv2d(in_filters,out_filters,1,stride=strides, bias=False)
+            self.skipbn = nn.BatchNorm2d(out_filters)
+        else:
+            self.skip=None
+
+        rep=[]
+
+        filters=in_filters
+        if grow_first:
+            rep.append(nn.ReLU(inplace=True))
+            rep.append(SeparableConv2d(in_filters,out_filters,3,stride=1,padding=dilation, dilation=dilation, bias=False))
+            rep.append(nn.BatchNorm2d(out_filters))
+            filters = out_filters
+
+        for i in range(reps-1):
+            rep.append(nn.ReLU(inplace=True))
+            rep.append(SeparableConv2d(filters,filters,3,stride=1,padding=dilation,dilation=dilation,bias=False))
+            rep.append(nn.BatchNorm2d(filters))
+
+        if not grow_first:
+            rep.append(nn.ReLU(inplace=True))
+            rep.append(SeparableConv2d(in_filters,out_filters,3,stride=1,padding=dilation,dilation=dilation,bias=False))
+            rep.append(nn.BatchNorm2d(out_filters))
+
+        if not start_with_relu:
+            rep = rep[1:]
+        else:
+            rep[0] = nn.ReLU(inplace=False)
+
+        if strides != 1:
+            rep.append(nn.MaxPool2d(3,strides,1))
+        self.rep = nn.Sequential(*rep)
+
+    def forward(self,inp):
+        x = self.rep(inp)
+
+        if self.skip is not None:
+            skip = self.skip(inp)
+            skip = self.skipbn(skip)
+        else:
+            skip = inp
+        x+=skip
+        return x
+
+
+class Xception(nn.Module):
+    """
+    Xception optimized for the ImageNet dataset, as specified in
+    https://arxiv.org/pdf/1610.02357.pdf
+    """
+    def __init__(self, num_classes=1000, replace_stride_with_dilation=None):
+        """ Constructor
+        Args:
+            num_classes: number of classes
+        """
+        super(Xception, self).__init__()
+
+        self.num_classes = num_classes
+        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, False]
+        if len(replace_stride_with_dilation) != 4:
+            raise ValueError("replace_stride_with_dilation should be None "
+                             "or a 4-element tuple, got {}".format(replace_stride_with_dilation))
+
+        self.conv1 = nn.Conv2d(3, 32, 3,2, 0, bias=False) # 1 / 2
+        self.bn1 = nn.BatchNorm2d(32)
+        self.relu1 = nn.ReLU(inplace=True)
+
+        self.conv2 = nn.Conv2d(32,64,3,bias=False)
+        self.bn2 = nn.BatchNorm2d(64)
+        self.relu2 = nn.ReLU(inplace=True)
+        #do relu here
+
+        self.block1=self._make_block(64,128,2,2,start_with_relu=False,grow_first=True, dilate=replace_stride_with_dilation[0]) # 1 / 4
+        self.block2=self._make_block(128,256,2,2,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[1]) # 1 / 8
+        self.block3=self._make_block(256,728,2,2,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2]) # 1 / 16
+
+        self.block4=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+        self.block5=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+        self.block6=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+        self.block7=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+
+        self.block8=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+        self.block9=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+        self.block10=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+        self.block11=self._make_block(728,728,3,1,start_with_relu=True,grow_first=True, dilate=replace_stride_with_dilation[2])
+
+        self.block12=self._make_block(728,1024,2,2,start_with_relu=True,grow_first=False, dilate=replace_stride_with_dilation[3]) # 1 / 32
+
+        self.conv3 = SeparableConv2d(1024,1536,3,1,1, dilation=self.dilation)
+        self.bn3 = nn.BatchNorm2d(1536)
+        self.relu3 = nn.ReLU(inplace=True)
+
+        #do relu here
+        self.conv4 = SeparableConv2d(1536,2048,3,1,1, dilation=self.dilation)
+        self.bn4 = nn.BatchNorm2d(2048)
+
+        self.fc = nn.Linear(2048, num_classes)
+
+        # #------- init weights --------
+        # for m in self.modules():
+        #     if isinstance(m, nn.Conv2d):
+        #         n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+        #         m.weight.data.normal_(0, math.sqrt(2. / n))
+        #     elif isinstance(m, nn.BatchNorm2d):
+        #         m.weight.data.fill_(1)
+        #         m.bias.data.zero_()
+        # #-----------------------------
+
+    def _make_block(self, in_filters,out_filters,reps,strides=1,start_with_relu=True,grow_first=True, dilate=False):
+        if dilate:
+            self.dilation *= strides
+            strides = 1
+        return Block(in_filters,out_filters,reps,strides,start_with_relu=start_with_relu,grow_first=grow_first, dilation=self.dilation)
+
+    def features(self, input):
+        x = self.conv1(input)
+        x = self.bn1(x)
+        x = self.relu1(x)
+
+        x = self.conv2(x)
+        x = self.bn2(x)
+        x = self.relu2(x)
+
+        x = self.block1(x)
+        x = self.block2(x)
+        x = self.block3(x)
+        x = self.block4(x)
+        x = self.block5(x)
+        x = self.block6(x)
+        x = self.block7(x)
+        x = self.block8(x)
+        x = self.block9(x)
+        x = self.block10(x)
+        x = self.block11(x)
+        x = self.block12(x)
+
+        x = self.conv3(x)
+        x = self.bn3(x)
+        x = self.relu3(x)
+
+        x = self.conv4(x)
+        x = self.bn4(x)
+        return x
+
+    def logits(self, features):
+        x = nn.ReLU(inplace=True)(features)
+
+        x = F.adaptive_avg_pool2d(x, (1, 1))
+        x = x.view(x.size(0), -1)
+        x = self.last_linear(x)
+        return x
+
+    def forward(self, input):
+        x = self.features(input)
+        x = self.logits(x)
+        return x
+
+
+def xception(num_classes=1000, pretrained='imagenet', replace_stride_with_dilation=None):
+    model = Xception(num_classes=num_classes, replace_stride_with_dilation=replace_stride_with_dilation)
+    if pretrained:
+        settings = pretrained_settings['xception'][pretrained]
+        assert num_classes == settings['num_classes'], \
+            "num_classes should be {}, but is {}".format(settings['num_classes'], num_classes)
+
+        model = Xception(num_classes=num_classes, replace_stride_with_dilation=replace_stride_with_dilation)
+        model.load_state_dict(model_zoo.load_url(settings['url']))
+
+    # TODO: ugly
+    model.last_linear = model.fc
+    del model.fc
+    return model
diff --git a/network/modeling.py b/network/modeling.py
@@ -1,8 +1,11 @@
 from .utils import IntermediateLayerGetter
 from ._deeplab import DeepLabHead, DeepLabHeadV3Plus, DeepLabV3
-from .backbone import resnet
-from .backbone import mobilenetv2
-from .backbone import hrnetv2
+from .backbone import (
+    resnet,
+    mobilenetv2,
+    hrnetv2,
+    xception
+)
 
 def _segm_hrnet(name, backbone_name, num_classes, pretrained_backbone):
 
@@ -53,6 +56,31 @@ def _segm_resnet(name, backbone_name, num_classes, output_stride, pretrained_bac
     model = DeepLabV3(backbone, classifier)
     return model
 
+
+def _segm_xception(name, backbone_name, num_classes, output_stride, pretrained_backbone):
+    if output_stride==8:
+        replace_stride_with_dilation=[False, False, True, True]
+        aspp_dilate = [12, 24, 36]
+    else:
+        replace_stride_with_dilation=[False, False, False, True]
+        aspp_dilate = [6, 12, 18]
+
+    backbone = xception.xception(pretrained= 'imagenet' if pretrained_backbone else False, replace_stride_with_dilation=replace_stride_with_dilation)
+
+    inplanes = 2048
+    low_level_planes = 128
+
+    if name=='deeplabv3plus':
+        return_layers = {'conv4': 'out', 'block1': 'low_level'}
+        classifier = DeepLabHeadV3Plus(inplanes, low_level_planes, num_classes, aspp_dilate)
+    elif name=='deeplabv3':
+        return_layers = {'conv4': 'out'}
+        classifier = DeepLabHead(inplanes , num_classes, aspp_dilate)
+    backbone = IntermediateLayerGetter(backbone, return_layers=return_layers)
+    model = DeepLabV3(backbone, classifier)
+    return model
+
+
 def _segm_mobilenet(name, backbone_name, num_classes, output_stride, pretrained_backbone):
     if output_stride==8:
         aspp_dilate = [12, 24, 36]
@@ -89,6 +117,8 @@ def _load_model(arch_type, backbone, num_classes, output_stride, pretrained_back
         model = _segm_resnet(arch_type, backbone, num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)
     elif backbone.startswith('hrnetv2'):
         model = _segm_hrnet(arch_type, backbone, num_classes, pretrained_backbone=pretrained_backbone)
+    elif backbone=='xception':
+        model = _segm_xception(arch_type, backbone, num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)
     else:
         raise NotImplementedError
     return model
@@ -131,6 +161,16 @@ def deeplabv3_mobilenet(num_classes=21, output_stride=8, pretrained_backbone=Tru
     """
     return _load_model('deeplabv3', 'mobilenetv2', num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)
 
+def deeplabv3_xception(num_classes=21, output_stride=8, pretrained_backbone=True, **kwargs):
+    """Constructs a DeepLabV3 model with a Xception backbone.
+
+    Args:
+        num_classes (int): number of classes.
+        output_stride (int): output stride for deeplab.
+        pretrained_backbone (bool): If True, use the pretrained backbone.
+    """
+    return _load_model('deeplabv3', 'xception', num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)
+
 
 # Deeplab v3+
 def deeplabv3plus_hrnetv2_48(num_classes=21, output_stride=4, pretrained_backbone=False): # no pretrained backbone yet
@@ -169,4 +209,14 @@ def deeplabv3plus_mobilenet(num_classes=21, output_stride=8, pretrained_backbone
         output_stride (int): output stride for deeplab.
         pretrained_backbone (bool): If True, use the pretrained backbone.
     """
-    return _load_model('deeplabv3plus', 'mobilenetv2', num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)
+    return _load_model('deeplabv3plus', 'mobilenetv2', num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)
+
+def deeplabv3plus_xception(num_classes=21, output_stride=8, pretrained_backbone=True):
+    """Constructs a DeepLabV3+ model with a Xception backbone.
+
+    Args:
+        num_classes (int): number of classes.
+        output_stride (int): output stride for deeplab.
+        pretrained_backbone (bool): If True, use the pretrained backbone.
+    """
+    return _load_model('deeplabv3plus', 'xception', num_classes, output_stride=output_stride, pretrained_backbone=pretrained_backbone)