File size: 7,194 Bytes
9e14838 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 | # -*- coding: utf-8 -*-
"""
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
"""
import os
import sys
if not (os.getcwd()) in sys.path:
sys.path.append(os.getcwd())
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
from ...builder import MODELS
from ..common import BN_MOMENTUM, conv_block
model_urls = {
"xception": "https://www.dropbox.com/s/1hplpzet9d7dv29/xception-c0a72b38.pth.tar?dl=1"
}
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, 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, 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, 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, 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(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
@MODELS.register_module()
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, **kwargs):
"""Constructor
Args:
num_classes: number of classes
"""
super(Xception, self).__init__()
self.num_classes = num_classes
self.conv1 = nn.Conv2d(3, 32, 3, 2, 0, bias=False)
self.bn1 = nn.BatchNorm2d(32)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(32, 64, 3, bias=False)
self.bn2 = nn.BatchNorm2d(64)
# do relu here
self.block1 = Block(64, 128, 2, 2, start_with_relu=False, grow_first=True)
self.block2 = Block(128, 256, 2, 2, start_with_relu=True, grow_first=True)
self.block3 = Block(256, 728, 2, 2, start_with_relu=True, grow_first=True)
self.block4 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block5 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block6 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block7 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block8 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block9 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block10 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block11 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
self.block12 = Block(728, 1024, 2, 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)
def forward(self, x):
x = self.conv1(x)
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)
x = self.relu(x)
x = F.adaptive_avg_pool2d(x, (1, 1))
x = x.view(x.size(0), -1)
# x = self.fc(x)
res = {}
res["cls"] = x
return res
def init_weights(self, pretrained=False):
if not pretrained:
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(2.0 / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
else:
state_dict = model_zoo.load_url(model_urls["xception"])
state_dict.pop("fc.weight")
state_dict.pop("fc.bias")
self.load_state_dict(state_dict, strict=False)
if __name__ == "__main__":
net = Xception()
input = torch.rand((1, 3, 224, 224))
out = net(input)
print(out["cls"].shape)
|