import torch.nn as nn
import torch
import torch.nn.functional as F
class GoogLeNet(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
super(GoogLeNet, self).__init__()
self.aux_logits = aux_logits
self.conv1 = BasicConv2d(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.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.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.maxpool4 = nn.MaxPool2d(3, 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)
if self.aux_logits:
self.aux1 = InceptionAux(512, num_classes)
self.aux2 = InceptionAux(528, num_classes)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(0.4)
self.fc = nn.Linear(1024, num_classes)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N x 3 x 224 x 224
x = self.conv1(x)
# N x 64 x 112 x 112
x = self.maxpool1(x)
# N x 64 x 56 x 56
x = self.conv2(x)
# N x 64 x 56 x 56
x = self.conv3(x)
# N x 192 x 56 x 56
x = self.maxpool2(x)
# N x 192 x 28 x 28
x = self.inception3a(x)
# N x 256 x 28 x 28
x = self.inception3b(x)
# N x 480 x 28 x 28
x = self.maxpool3(x)
# N x 480 x 14 x 14
x = self.inception4a(x)
# N x 512 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux1 = self.aux1(x)
x = self.inception4b(x)
# N x 512 x 14 x 14
x = self.inception4c(x)
# N x 512 x 14 x 14
x = self.inception4d(x)
# N x 528 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux2 = self.aux2(x)
x = self.inception4e(x)
# N x 832 x 14 x 14
x = self.maxpool4(x)
# N x 832 x 7 x 7
x = self.inception5a(x)
# N x 832 x 7 x 7
x = self.inception5b(x)
# N x 1024 x 7 x 7
x = self.avgpool(x)
# N x 1024 x 1 x 1
x = torch.flatten(x, 1)
# N x 1024
x = self.dropout(x)
x = self.fc(x)
# N x 1000 (num_classes)
if self.training and self.aux_logits: # eval model lose this layer
return x, aux2, aux1
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
class Inception(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(Inception, self).__init__()
self.branch1 = BasicConv2d(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) # 保证输出大小等于输入大小
)
self.branch3 = nn.Sequential(
BasicConv2d(in_channels, ch5x5red, kernel_size=1),
# 在官方的实现中,其实是3x3的kernel并不是5x5,这里我也懒得改了,具体可以参考下面的issue
# Please see https://github.com/pytorch/vision/issues/906 for details.
BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2) # 保证输出大小等于输入大小
)
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
BasicConv2d(in_channels, pool_proj, kernel_size=1)
)
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 torch.cat(outputs, 1)
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, num_classes)
def forward(self, x):
# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
x = self.averagePool(x)
# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
x = self.conv(x)
# N x 128 x 4 x 4
x = torch.flatten(x, 1)
x = F.dropout(x, 0.5, training=self.training)
# N x 2048
x = F.relu(self.fc1(x), inplace=True)
x = F.dropout(x, 0.5, training=self.training)
# N x 1024
x = self.fc2(x)
# N x num_classes
return x
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.relu(x)
return x
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
googlenet木薯病.zip (2000个子文件)
BACTERAILBLIGHT3_094.jpg 263KB
BACTERIALBLIGHT2_190.jpg 259KB
BACTERAILBLIGHT5_094.jpg 259KB
BACTERAILBLIGHT4_190.jpg 259KB
BACTERAILBLIGHT4_094.jpg 259KB
BACTERIALBLIGHT2_076.jpg 254KB
BACTERAILBLIGHT5_172.jpg 254KB
BACTERAILBLIGHT3_076.jpg 254KB
BACTERIALBLIGHT1_172.jpg 254KB
BACTERAILBLIGHT5_076.jpg 254KB
BACTERAILBLIGHT4_172.jpg 254KB
BACTERIALBLIGHT1_076.jpg 254KB
BACTERAILBLIGHT3_172.jpg 254KB
BACTERAILBLIGHT5_098.jpg 253KB
BACTERAILBLIGHT3_078.jpg 250KB
BACTERIALBLIGHT1_174.jpg 250KB
BACTERAILBLIGHT4_078.jpg 248KB
BACTERAILBLIGHT5_078.jpg 248KB
BACTERIALBLIGHT2_078.jpg 248KB
BACTERIALBLIGHT1_176.jpg 237KB
BACTERAILBLIGHT4_188.jpg 234KB
BACTERAILBLIGHT5_188.jpg 234KB
BACTERIALBLIGHT1_090.jpg 233KB
BACTERIALBLIGHT1_074.jpg 233KB
BACTERIALBLIGHT1_086.jpg 233KB
BACTERAILBLIGHT3_092.jpg 233KB
BACTERAILBLIGHT3_184.jpg 233KB
BACTERAILBLIGHT3_180.jpg 233KB
BACTERAILBLIGHT3_186.jpg 233KB
BACTERAILBLIGHT3_088.jpg 233KB
BACTERAILBLIGHT3_084.jpg 233KB
BACTERIALBLIGHT1_186.jpg 233KB
BACTERIALBLIGHT1_182.jpg 233KB
BACTERIALBLIGHT1_184.jpg 233KB
BACTERIALBLIGHT1_180.jpg 233KB
BACTERIALBLIGHT1_092.jpg 233KB
BACTERAILBLIGHT5_074.jpg 232KB
BACTERAILBLIGHT5_088.jpg 232KB
BACTERAILBLIGHT5_084.jpg 232KB
BACTERIALBLIGHT2_084.jpg 232KB
BACTERIALBLIGHT2_090.jpg 232KB
BACTERIALBLIGHT2_088.jpg 232KB
BACTERAILBLIGHT4_182.jpg 232KB
BACTERAILBLIGHT4_186.jpg 232KB
BACTERAILBLIGHT4_184.jpg 232KB
BACTERAILBLIGHT4_170.jpg 232KB
BACTERIALBLIGHT2_186.jpg 232KB
BACTERIALBLIGHT2_170.jpg 232KB
BACTERAILBLIGHT4_086.jpg 232KB
BACTERAILBLIGHT4_084.jpg 232KB
BACTERAILBLIGHT5_170.jpg 232KB
BROWNSPOT2_002.jpg 231KB
BROWNSPOT5_102.jpg 230KB
BROWNSPOT3_102.jpg 230KB
BROWNSPOT3_002.jpg 230KB
BLAST6_034.jpg 229KB
BLAST2_034.jpg 229KB
BLAST4_114.jpg 229KB
BACTERAILBLIGHT3_178.jpg 229KB
BACTERIALBLIGHT1_082.jpg 229KB
BACTERIALBLIGHT2_080.jpg 228KB
BACTERAILBLIGHT4_176.jpg 228KB
BACTERIALBLIGHT1_192.jpg 228KB
BACTERIALBLIGHT2_192.jpg 228KB
BACTERAILBLIGHT3_192.jpg 228KB
BACTERAILBLIGHT5_192.jpg 228KB
BACTERIALBLIGHT1_096.jpg 228KB
BACTERIALBLIGHT2_176.jpg 228KB
BACTERAILBLIGHT4_080.jpg 228KB
BACTERAILBLIGHT5_096.jpg 228KB
BACTERAILBLIGHT4_192.jpg 228KB
BROWNSPOT3_008.jpg 227KB
BROWNSPOT5_108.jpg 227KB
brownspot_orig_002.jpg 227KB
BROWNSPOT6_102.jpg 227KB
BROWNSPOT7_002.jpg 227KB
BROWNSPOT6_002.jpg 227KB
BROWNSPOT7_102.jpg 227KB
BLAST2_040.jpg 225KB
BLAST2_120.jpg 225KB
BLAST2_036.jpg 223KB
BLAST4_116.jpg 223KB
BLAST6_116.jpg 223KB
BLAST2_088.jpg 223KB
BLAST3_116.jpg 223KB
BLAST7_116.jpg 223KB
BACTERAILBLIGHT5_082.jpg 223KB
BLAST7_036.jpg 222KB
BLAST3_036.jpg 222KB
BROWNSPOT6_008.jpg 218KB
BLAST4_012.jpg 215KB
BACTERAILBLIGHT5_100.jpg 215KB
BACTERAILBLIGHT4_100.jpg 215KB
BACTERIALBLIGHT2_100.jpg 215KB
BACTERIALBLIGHT2_196.jpg 215KB
BLAST2_024.jpg 215KB
BLAST4_104.jpg 215KB
BLAST6_092.jpg 215KB
BLAST2_104.jpg 215KB
BLAST3_088.jpg 213KB
共 2000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 20
资源评论
sjx_alo
- 粉丝: 1w+
- 资源: 1208
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功