keras resnet
from keras.layers import Input, Conv2D, BatchNormalization, Activation, ZeroPadding2D
from keras.layers import MaxPool2D, GlobalAveragePooling2D, Dense
from keras.layers import add # merge
from keras.models import Model, Sequential
from keras.utils import plot_model
"""implement of Pytorch ResNet"""
def basic_block(input_tensor, filters, stride=1, downsample=None):
residual = input_tensor
# 3x3
x = Conv2D(filters, kernel_size=3, strides=stride, padding='same')(input_tensor)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
# 3x3
x = Conv2D(filters, kernel_size=3, padding='same')(x)
x = BatchNormalization(axis=3)(x)
# layer 内部没有 fm size 变化，layer连接处有
if downsample: # 类比 resnet50，identity_block shortcut 没有 downsample，而 conv_block 有
residual = downsample(input_tensor)
x = add([x, residual])
x = Activation('relu')(x)
return x
def bottleneck(input_tensor, filters, stride=1, downsample=None):
residual = input_tensor
# 1x1
x = Conv2D(filters, kernel_size=1, padding='same')(input_tensor)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
print(x.shape, residual.shape)
# 3x3 core
x = Conv2D(filters, kernel_size=3, strides=stride, padding='same')(x)
x = BatchNormalization(axis=3)(x)
x = Activation('relu')(x)
print(x.shape, residual.shape)
# 1x1
x = Conv2D(filters * 4, kernel_size=1, padding='same')(x) # fms * 4
x = BatchNormalization(axis=3)(x)
if downsample:
residual = downsample(input_tensor)
print(x.shape, residual.shape)
x = add([x, residual])
x = Activation('relu')(x)
return x
def make_layer(input_tensor, block, filters, blocks, stride=1):
"""
:param input_tensor:
:param block: basic_block, bottleneck
:param filters: 输出通道数
:param blocks: block 重复次数
:param stride: stage345, stride=2; stage2, 第一层有maxpool，所以stride=1
:return: layer output
"""
global in_filters
downsample = None
expansion = 4 if block.__name__ == 'bottleneck' else 1
"""residual 是否需要下采样
basic_block
- stage2, stride=1, 并且 in_filters = filters * expansion，所以不用 downsample
bottleneck
- stage2，虽然 stride=1，但是 in_filters != filters * expansion，需要 downsample 改变 channel
- stride != 1，需要把 输入 size/2 再和输出相加，stage3,4,5 每个layer的第1个block
所以第2个条件 对于不同结构 block 操作不同
"""
if stride != 1 or in_filters != filters * expansion:
downsample = Sequential([
Conv2D(filters * expansion, kernel_size=1, strides=stride, padding='same'),
BatchNormalization(axis=3)
])
in_filters = filters * expansion # next layer input filters
# 对于 stage2，虽然 stride 单独列出，但是也没改变 fm size
out = block(input_tensor, filters=filters, stride=stride, downsample=downsample) # layer开始部分
for i in range(1, blocks):
out = block(out, filters=filters) # layer内部重复部分 不需要 downsample，stride=1
return out
in_filters = 64
def ResNet(input_tensor, block, layers, include_top=True, classes=1000):
# stage1
x = Conv2D(64, (7, 7), strides=(2, 2), # 224->112
padding='same',
kernel_initializer='he_normal',
name='conv1')(input_tensor)
x = BatchNormalization(axis=3, name='conv1_bn')(x) # channel last
x = Activation('relu', name='conv1_relu')(x)
x = MaxPool2D((3, 3), strides=(2, 2), padding='same')(x) # 112->56
x = make_layer(x, block, filters=64, blocks=layers[0]) # stage 2
x = make_layer(x, block, filters=128, blocks=layers[1], stride=2) # stage 3
x = make_layer(x, block, filters=256, blocks=layers[2], stride=2) # stage 4
x = make_layer(x, block, filters=512, blocks=layers[3], stride=2) # stage 5
# fc
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
print(x.shape)
model = Model(inputs=[inputs], outputs=[x])
return model
inputs = Input(shape=(224, 224, 3))
resnet18 = ResNet(inputs, block=basic_block, layers=[2, 2, 2, 2], include_top=False)
plot_model(resnet18, to_file='resnet18.png', show_shapes=True)
resnet50 = ResNet(inputs, block=bottleneck, layers=[3, 4, 6, 3], include_top=False)
plot_model(resnet50, to_file='resnet50.png', show_shapes=True)
Pytorch resnet
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
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_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def resnet18(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
return model
def resnet34(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
return model
def resnet50(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
return model
def resnet101(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
return model
def resnet152(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
return model
网友评论