PyTrch深度学习简明实战17 - Inception
2023-03-29 本文已影响0人
薛东弗斯
学习笔记18：Inception模型 - pbc的成长之路 - 博客园 (cnblogs.com)
Inception网络，考虑到不同大小卷积核的影响。
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
1x1的卷积，图像大小不变，但channel 缩减，从而减少计算量
import torch
from torch import nn
import torch.nn.functional as F
import torchvision
# 定义基础卷积模型 卷积+BN+激活
class Basicconv(nn.Module):
def __init__(self,in_channels,out_channels,**kwargs): # **kwargs 代表其它参数。比如卷积核等
super(Basicconv,self).__init__() # 继承父类属性
self.conv = nn.Conv2d(in_channels,out_channels,bias=False,**kwargs) # 对于卷积层，偏置无影响，为了节约资源，此处bias=False
# BN层最后对数据做了平移变换。 乘以权重 + 偏置。 这样无论前面卷积是否有偏置，后面的BN层仍然跟着有偏置。因此conv层偏置没有任何影响。
self.bn = nn.BatchNorm2d(out_channels)
def forward(self,x):
x = self.conv(x)
self.bn(x)
return F.relu(x,inplace=True) # inplace=True 直接改变原始数据
class InceptionBlock(nn.Module):
def __init__(self,in_channels,pool_features): # pool_features 定义最后输出多少个特征
super(InceptionBlock,self).__init__() # 继承父类属性
self.b1x1 = Basicconv(in_channels,64,kernel_size=1) # 第1个分支，1x1卷积
self.b3x3_1 = Basicconv(in_channels,64,kernel_size=1) # 先经过1x1卷积，用于缩减图片channel，减少计算量
self.b3x3_2 = Basicconv(64,96,kernel_size=3,padding=1) # 后经过3x3卷积。 kernel_size定义卷积核大小。
# pytorch默认的填充方式为‘Valid’，每次卷积都要下降k-1个像素。对于3x3卷积，长/宽像素都会减少2，因此padding应为1，向四周各填充1个像素。
# padding=1，上下左右各填充1各像素
self.b5x5_1 = Basicconv(in_channels,48,kernel_size=1) # 先经过1x1卷积
self.b5x5_2 = Basicconv(48,64,kernel_size=5,padding=2) # 经过5x5 卷积
self.b_pool = Basicconv(in_channels,pool_features,kernel_size=1) # 池化
def forward(self,x): # 前向传播
b_1x1_out = self.b1x1(x)
b_3x3 = self.b_3x3_1(x) # 先1x1 卷积核
b_3x3_out = self.b_3x3_2(b_3x3) # 后3x3 卷积核
b_5x5 = self.b_5x5_1(x) #先1x1 卷积核
b_5x5_out = self.b_5x5_2(b_5x5) # 后5x5 卷积核
b_pool_out = F.max_pool2d(x,kernel_size=3,stride=1,padding=1) # 先3x3 最大池化，确保输入输出大小相同
b_pool_out = self.b_pool(b_pool_out) # 1x1卷积
outputs =[b_1x1_out,b_3x3_out,b_5x5_out,b_pool_out]
return torch.cat(outputs,dim=1) # 返回的第0维度是batch_size. 第1维度是特征
my_inception_block = InceptionBlock(32,64)
上面是基于特征提取进行的训练。精度不高。 如果使用数据增强，则需要直接使用预训练模型，在预训练模型基础上改变FC层的classfier，再进行训练
1》 使用数据增强，是没办法先提取特征的。
2）一旦使用先提取特征，再进行训练分类模型，整个训练过程会加速。因为输入的都是提取好的特征，并不需要对图片进行预处理、加载，不需要图片经过卷积
提取特征，直接使用特征创建全连接模型
model = torchvision.models.inception_v3(pretrained=True)
Inception3(
(Conv2d_1a_3x3): BasicConv2d(
(conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_2a_3x3): BasicConv2d(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_2b_3x3): BasicConv2d(
(conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(maxpool1): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(Conv2d_3b_1x1): BasicConv2d(
(conv): Conv2d(64, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(80, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(Conv2d_4a_3x3): BasicConv2d(
(conv): Conv2d(80, 192, kernel_size=(3, 3), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(maxpool2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
(Mixed_5b): InceptionA(
(branch1x1): BasicConv2d(
(conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_1): BasicConv2d(
(conv): Conv2d(192, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_2): BasicConv2d(
(conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_5c): InceptionA(
(branch1x1): BasicConv2d(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_1): BasicConv2d(
(conv): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_2): BasicConv2d(
(conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_5d): InceptionA(
(branch1x1): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_1): BasicConv2d(
(conv): Conv2d(288, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(48, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch5x5_2): BasicConv2d(
(conv): Conv2d(48, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6a): InceptionB(
(branch3x3): BasicConv2d(
(conv): Conv2d(288, 384, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(288, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(64, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3): BasicConv2d(
(conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(96, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6b): InceptionC(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(128, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(128, 128, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(128, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6c): InceptionC(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6d): InceptionC(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(160, 160, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(160, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(160, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_6e): InceptionC(
(branch1x1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_2): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7_3): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_2): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_3): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_4): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7dbl_5): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(AuxLogits): InceptionAux(
(conv0): BasicConv2d(
(conv): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(conv1): BasicConv2d(
(conv): Conv2d(128, 768, kernel_size=(5, 5), stride=(1, 1), bias=False)
(bn): BatchNorm2d(768, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(fc): Linear(in_features=768, out_features=1000, bias=True)
)
(Mixed_7a): InceptionD(
(branch3x3_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2): BasicConv2d(
(conv): Conv2d(192, 320, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_1): BasicConv2d(
(conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_2): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(1, 7), stride=(1, 1), padding=(0, 3), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_3): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(7, 1), stride=(1, 1), padding=(3, 0), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch7x7x3_4): BasicConv2d(
(conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_7b): InceptionE(
(branch1x1): BasicConv2d(
(conv): Conv2d(1280, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_1): BasicConv2d(
(conv): Conv2d(1280, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(1280, 448, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(448, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(448, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(1280, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(Mixed_7c): InceptionE(
(branch1x1): BasicConv2d(
(conv): Conv2d(2048, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(320, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_1): BasicConv2d(
(conv): Conv2d(2048, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3_2b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_1): BasicConv2d(
(conv): Conv2d(2048, 448, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(448, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_2): BasicConv2d(
(conv): Conv2d(448, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3a): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(1, 3), stride=(1, 1), padding=(0, 1), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch3x3dbl_3b): BasicConv2d(
(conv): Conv2d(384, 384, kernel_size=(3, 1), stride=(1, 1), padding=(1, 0), bias=False)
(bn): BatchNorm2d(384, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
(branch_pool): BasicConv2d(
(conv): Conv2d(2048, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(192, eps=0.001, momentum=0.1, affine=True, track_running_stats=True)
)
)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(dropout): Dropout(p=0.5, inplace=False)
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)
