Start working on Xception

pytorch/pytorchcv/models/others/oth_xception.py

@@ -0,0 +1,273 @@
+"""
+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__ = ['oth_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):
+        super(Block, self).__init__()
+
+        if out_filters != in_filters or strides != 1:
+            self.skip = nn.Conv2d(
+                in_filters,
+                out_filters,
+                kernel_size=1,
+                stride=strides,
+                bias=False)
+            self.skipbn = nn.BatchNorm2d(out_filters)
+        else:
+            self.skip = None
+
+        self.relu = nn.ReLU(inplace=True)
+        rep=[]
+
+        filters=in_filters
+        if grow_first:
+            rep.append(self.relu)
+            rep.append(SeparableConv2d(
+                in_filters,
+                out_filters,
+                kernel_size=3,
+                stride=1,
+                padding=1,
+                bias=False))
+            rep.append(nn.BatchNorm2d(out_filters))
+            filters = out_filters
+
+        for i in range(reps-1):
+            rep.append(self.relu)
+            rep.append(SeparableConv2d(
+                filters,
+                filters,
+                kernel_size=3,
+                stride=1,
+                padding=1,
+                bias=False))
+            rep.append(nn.BatchNorm2d(filters))
+
+        if not grow_first:
+            rep.append(self.relu)
+            rep.append(SeparableConv2d(
+                in_filters,
+                out_filters,
+                kernel_size=3,
+                stride=1,
+                padding=1,
+                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(
+                kernel_size=3,
+                stride=strides,
+                padding=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):
+        """ Constructor
+        Args:
+            num_classes: number of classes
+        """
+        super(Xception, self).__init__()
+        self.num_classes = num_classes
+
+        self.conv1 = nn.Conv2d(in_channels=3, out_channels=32, kernel_size=3,stride=2, padding=0, bias=False)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.relu = nn.ReLU(inplace=True)
+
+        self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size=3,bias=False)
+        self.bn2 = nn.BatchNorm2d(64)
+        #do relu here
+
+        self.block1=Block(64,128,reps=2,strides=2,start_with_relu=False,grow_first=True)
+        self.block2=Block(128,256,reps=2,strides=2,start_with_relu=True,grow_first=True)
+        self.block3=Block(256,728,reps=2,strides=2,start_with_relu=True,grow_first=True)
+
+        self.block4=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+        self.block5=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+        self.block6=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+        self.block7=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+
+        self.block8=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+        self.block9=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+        self.block10=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+        self.block11=Block(728,728,reps=3,strides=1,start_with_relu=True,grow_first=True)
+
+        self.block12=Block(728,1024,reps=2,strides=2,start_with_relu=True,grow_first=False)
+
+        self.conv3 = SeparableConv2d(1024,1536,3,1,1)
+        self.bn3 = nn.BatchNorm2d(1536)
+
+        #do relu here
+        self.conv4 = SeparableConv2d(1536,2048,3,1,1)
+        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 features(self, input):
+        x = self.conv1(input)
+        x = self.bn1(x)
+        x = self.relu(x)
+
+        x = self.conv2(x)
+        x = self.bn2(x)
+        x = self.relu(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.relu(x)
+
+        x = self.conv4(x)
+        x = self.bn4(x)
+        return x
+
+    def logits(self, features):
+        x = self.relu(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 oth_xception(num_classes=1000, pretrained='imagenet'):
+    model = Xception(num_classes=num_classes)
+    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)
+        model.load_state_dict(model_zoo.load_url(settings['url']))
+
+        model.input_space = settings['input_space']
+        model.input_size = settings['input_size']
+        model.input_range = settings['input_range']
+        model.mean = settings['mean']
+        model.std = settings['std']
+
+    # TODO: ugly
+    model.last_linear = model.fc
+    del model.fc
+    return model