- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者：K同学啊 | 接辅导、项目定制
目录
0. 总结
数据导入及处理部分：本次数据导入没有使用torchvision自带的数据集，需要将原始数据进行处理包括数据导入，查看数据分类情况，定义transforms，进行数据类型转换等操作。
划分数据集：划定训练集测试集后，再使用torch.utils.data中的DataLoader()分别加载上一步处理好的训练及测试数据，查看批处理维度.
模型构建部分：Inception V3
设置超参数：在这之前需要定义损失函数，学习率（动态学习率），以及根据学习率定义优化器（例如SGD随机梯度下降），用来在训练中更新参数，最小化损失函数。
定义训练函数：函数的传入的参数有四个，分别是设置好的DataLoader(),定义好的模型，损失函数，优化器。函数内部初始化损失准确率为0，接着开始循环，使用DataLoader()获取一个批次的数据，对这个批次的数据带入模型得到预测值，然后使用损失函数计算得到损失值。接下来就是进行反向传播以及使用优化器优化参数，梯度清零放在反向传播之前或者是使用优化器优化之后都是可以的，一般是默认放在反向传播之前。
定义测试函数：函数传入的参数相比训练函数少了优化器，只需传入设置好的DataLoader(),定义好的模型，损失函数。此外除了处理批次数据时无需再设置梯度清零、返向传播以及优化器优化参数，其余部分均和训练函数保持一致。
训练过程：定义训练次数，有几次就使用整个数据集进行几次训练，初始化四个空list分别存储每次训练及测试的准确率及损失。使用model.train()开启训练模式，调用训练函数得到准确率及损失。使用model.eval()将模型设置为评估模式，调用测试函数得到准确率及损失。接着就是将得到的训练及测试的准确率及损失存储到相应list中并合并打印出来，得到每一次整体训练后的准确率及损失。
结果可视化
模型的保存，调取及使用。在PyTorch中，通常使用 torch.save(model.state_dict(), ‘model.pth’) 保存模型的参数，使用 model.load_state_dict(torch.load(‘model.pth’)) 加载参数。
需要改进优化的地方：确保模型和数据的一致性，都存到GPU或者CPU;注意numclasses不要直接用默认的1000，需要根据实际数据集改进；实例化模型也要注意numclasses这个参数；此外注意测试模型需要用（3,224,224）3表示通道数，这和tensorflow定义的顺序是不用的（224,224,3），做代码转换时需要注意。
关于调优（十分重要）：本次将测试集准确率提升到了96.03%（随机种子设置为42）
1：使用多卡不一定比单卡效果好，需要继续调优
2：本次微调参数主要调整了两点一是初始学习率从1e-4 增大为了3e-4;其次是原来图片预处理只加入了随机水平翻转，本次加入了小角度的随机翻转，随机缩放剪裁，光照变化等，发现有更好的效果。测试集准确率有了很大的提升。从训练后的准确率图像也可以看到，训练准确率和测试准确率很接近甚至能够超过。之前没有做这个改进之前，都是训练准确率远大于测试准确率。
有个疑问是为啥必须要把图片尺寸设置为（299，299）？（244，244）会报错
关键代码示例：
import torchvision.transforms as transforms
# 定义猴痘识别的 transforms
train_transforms = transforms.Compose([
transforms.Resize([299, 299]), # 统一图片尺寸
transforms.RandomHorizontalFlip(p=0.5), # 随机水平翻转
transforms.RandomRotation(degrees=15), # 小角度随机旋转
transforms.RandomResizedCrop(size=299, scale=(0.8, 1.2)), # 随机缩放裁剪
transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.1), # 光照变化
transforms.ToTensor(), # 转换为 Tensor 格式
transforms.Normalize( # 标准化
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
])
Inception V1 简介
什么是Inception V1？
Inception V1，也被称为GoogLeNet，是Google在2014年ILSVRC比赛中提出的一种卷积神经网络（CNN）架构，并且在比赛中获得了冠军。与当时流行的VGGNet相比，Inception V1在保持相似性能的同时，显著减少了参数数量，从而提高了计算效率。
Inception Module的核心思想
Inception V1的核心是Inception Module，它通过并行的卷积操作在同一层提取不同尺度的特征。这种设计不仅增加了网络的深度，还有效地捕捉了多种特征信息。
具体来说，一个Inception Module通常包含以下几个分支：
- 1x1卷积分支：用于降低输入特征图的通道数，减少计算量。
- 1x1卷积后接3x3卷积分支：先用1x1卷积降维，再进行3x3卷积提取特征。
- 1x1卷积后接5x5卷积分支：类似于3x3分支，但使用更大的卷积核以捕捉更大范围的特征。
- 3x3最大池化后接1x1卷积分支：先进行池化操作，再用1x1卷积进行特征整合。
通过将这些分支的输出在通道维度上拼接，Inception Module能够在同一层次上整合多种尺度的信息，提升模型的表达能力。
1x1卷积的作用
1x1卷积主要用于降维，即减少特征图的通道数。这不仅降低了网络的参数量和计算量，还间接增加了网络的深度，有助于提升模型性能。例如：
- 原始输入：100x100x128
- 经过1x1卷积降维到32通道，再进行5x5卷积，输出仍为100x100x256
- 参数量由原来的约8.192×10⁹降低到2.048×10⁹
辅助分类器
Inception V1还引入了辅助分类器，主要有两个作用：
- 缓解梯度消失：通过在中间层添加分类器，帮助梯度更好地传播。
- 模型融合：将中间层的输出用于分类，增强模型的泛化能力。
不过，在实际应用中，这些辅助分类器通常在训练过程中使用，推理时会被去掉。
Inception V3 简介
Inception v3由谷歌研究员Christian Szegedy等人在2015年的论文《Rethinking the Inception Architecture for Computer Vision》中提出。Inception v3是Inception网络系列的第三个版本，它在ImageNet图像识别竞赛中取得了优异成绩，尤其是在大规模图像识别任务中表现出色。
Inception v3的主要特点如下：
1：更深的网络结构：Inception v3比之前的Inception网络结构更深，包含了48层卷积层。这使得网络可以提取更多层次的特征，从而在图像识别任务上取得更好的效果。
2：使用Factorized Convolutions：Inception v3采用了Factorized Convolutions（分解卷积），将较大的卷积核分解为多个较小的卷积核。这种方法可以降低网络的参数数量，减少计算复杂度，同时保持良好的性能。
3：使用Batch Normalization：Inceptionv3在每个卷积层之后都添加了Batch Normalization（BN），这有助于网络的收敛和泛化能力。BN可以减少Internal Covariate Shift（内部协变量偏移）现象，加快训练速度，同时提高模型的鲁棒性。
4：辅助分类器：Inception v3引入了辅助分类器，可以在网络训练过程中提供额外的梯度信息，帮助网络更好地学习特征。辅助分类器位于网络的某个中间层，其输出会与主分类器的输出进行加权融合，从而得到最终的预测结果。
5：基于RMSProp的优化器：Inception v3使用了RMSProp优化器进行训练。相比于传统的随机梯度下降（SGD）方法，RMSProp可以自适应地调整学习率，使得训练过程更加稳定，收敛速度更快。
Inception v3在图像分类、物体检测和图像分割等计算机视觉任务中均取得了显著的效果。然而，由于其较大的网络结构和计算复杂度，Inception v3在实际应用中可能需要较高的硬件要求。
import torch
import torch.nn as nn
import torchvision
from torchvision import datasets,transforms
from torch.utils.data import DataLoader
import torchvision.models as models
import torch.nn.functional as F
from collections import OrderedDict
import os,PIL,pathlib
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore') # 忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.dpi'] = 100 # 分辨率
1. 设置GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
device(type='cuda')
2. 导入数据及处理部分
# 获取数据分布情况
path_dir = './data/weather_recognize/weather_photos/'
path_dir = pathlib.Path(path_dir)
paths = list(path_dir.glob('*'))
# classNames = [str(path).split("\\")[-1] for path in paths] # ['Bananaquit', 'Black Skimmer', 'Black Throated Bushtiti', 'Cockatoo']
classNames = [path.parts[-1] for path in paths]
classNames
['cloudy', 'rain', 'shine', 'sunrise']
# 定义transforms 并处理数据
# train_transforms = transforms.Compose([
# transforms.Resize([224,224]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
# transforms.ToTensor(), # 将PIL Image 或 numpy.ndarray 装换为tensor,并归一化到[0,1]之间
# transforms.Normalize( # 标准化处理 --> 转换为标准正太分布（高斯分布），使模型更容易收敛
# mean = [0.485,0.456,0.406], # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
# std = [0.229,0.224,0.225]
# )
# ])
# 定义猴痘识别的 transforms 并处理数据
train_transforms = transforms.Compose([
transforms.Resize([299, 299]), # 统一图片尺寸
transforms.RandomHorizontalFlip(p=0.5), # 随机水平翻转
transforms.RandomRotation(degrees=15), # 小角度随机旋转
transforms.RandomResizedCrop(size=299, scale=(0.8, 1.2)), # 随机缩放裁剪
transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.1), # 光照变化
transforms.ToTensor(), # 转换为 Tensor 格式
transforms.Normalize( # 标准化
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
])
test_transforms = transforms.Compose([
transforms.Resize([299,299]),
transforms.ToTensor(),
transforms.Normalize(
mean = [0.485,0.456,0.406],
std = [0.229,0.224,0.225]
)
])
total_data = datasets.ImageFolder('./data/weather_recognize/weather_photos/',transform = train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 1125
Root location: ./data/weather_recognize/weather_photos/
StandardTransform
Transform: Compose(
Resize(size=[299, 299], interpolation=bilinear, max_size=None, antialias=True)
RandomHorizontalFlip(p=0.5)
RandomRotation(degrees=[-15.0, 15.0], interpolation=nearest, expand=False, fill=0)
RandomResizedCrop(size=(299, 299), scale=(0.8, 1.2), ratio=(0.75, 1.3333), interpolation=bilinear, antialias=True)
ColorJitter(brightness=(0.8, 1.2), contrast=(0.8, 1.2), saturation=(0.9, 1.1), hue=None)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
3. 划分数据集
# 设置随机种子
torch.manual_seed(42)
# 划分数据集
train_size = int(len(total_data) * 0.8)
test_size = len(total_data) - train_size
train_dataset,test_dataset = torch.utils.data.random_split(total_data,[train_size,test_size])
train_dataset,test_dataset
(<torch.utils.data.dataset.Subset at 0x29e06793df0>,
<torch.utils.data.dataset.Subset at 0x29e06793dc0>)
# 定义DataLoader用于数据集的加载
batch_size = 32 # 如使用多显卡，请确保 batch_size 是显卡数量的倍数。
train_dl = torch.utils.data.DataLoader(
train_dataset,
batch_size = batch_size,
shuffle = True,
num_workers = 1
)
test_dl = torch.utils.data.DataLoader(
test_dataset,
batch_size = batch_size,
shuffle = True,
num_workers = 1
)
# 观察数据维度
for X,y in test_dl:
print("Shape of X [N,C,H,W]: ",X.shape)
print("Shape of y: ", y.shape,y.dtype)
break
Shape of X [N,C,H,W]: torch.Size([32, 3, 299, 299])
Shape of y: torch.Size([32]) torch.int64
4. 模型构建部分
import torch
import torch.nn as nn
import torch.nn.functional as F
class InceptionA(nn.Module):
def __init__(self, in_channels, pool_features):
super(InceptionA, self).__init__()
self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1) # 1
self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1)
self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2)
self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)
self.branch_pool = BasicConv2d(in_channels, pool_features, kernel_size=1)
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch5x5 = self.branch5x5_1(x)
branch5x5 = self.branch5x5_2(branch5x5)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
return torch.cat(outputs, 1)
class InceptionB(nn.Module):
def __init__(self, in_channels, channels_7x7):
super(InceptionB, self).__init__()
self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1)
c7 = channels_7x7
self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1)
self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1)
self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1, 7), padding=(0, 3))
self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch7x7 = self.branch7x7_1(x)
branch7x7 = self.branch7x7_2(branch7x7)
branch7x7 = self.branch7x7_3(branch7x7)
branch7x7dbl = self.branch7x7dbl_1(x)
branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
return torch.cat(outputs, 1)
class InceptionC(nn.Module):
def __init__(self, in_channels):
super(InceptionC, self).__init__()
self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1)
self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1)
self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))
self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1)
self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1)
self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))
self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)
def forward(self, x):
branch1x1 = self.branch1x1(x)
branch3x3 = self.branch3x3_1(x)
branch3x3 = [
self.branch3x3_2a(branch3x3),
self.branch3x3_2b(branch3x3),
]
branch3x3 = torch.cat(branch3x3, 1)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = [
self.branch3x3dbl_3a(branch3x3dbl),
self.branch3x3dbl_3b(branch3x3dbl),
]
branch3x3dbl = torch.cat(branch3x3dbl, 1)
branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
branch_pool = self.branch_pool(branch_pool)
outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
return torch.cat(outputs, 1)
class ReductionA(nn.Module):
def __init__(self, in_channels):
super(ReductionA, self).__init__()
self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2)
self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, stride=2)
def forward(self, x):
branch3x3 = self.branch3x3(x)
branch3x3dbl = self.branch3x3dbl_1(x)
branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch3x3dbl, branch_pool]
return torch.cat(outputs, 1)
class ReductionB(nn.Module):
def __init__(self, in_channels):
super(ReductionB, self).__init__()
self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2)
self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
self.branch7x7x3_2 = BasicConv2d(192, 192, kernel_size=(1, 7), padding=(0, 3))
self.branch7x7x3_3 = BasicConv2d(192, 192, kernel_size=(7, 1), padding=(3, 0))
self.branch7x7x3_4 = BasicConv2d(192, 192, kernel_size=3, stride=2)
def forward(self, x):
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)
branch7x7x3 = self.branch7x7x3_1(x)
branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
branch7x7x3 = self.branch7x7x3_4(branch7x7x3)
branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)
outputs = [branch3x3, branch7x7x3, branch_pool]
return torch.cat(outputs, 1)
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
self.conv0 = BasicConv2d(in_channels, 128, kernel_size=1)
self.conv1 = BasicConv2d(128, 768, kernel_size=5)
self.conv1.stddev = 0.01
self.fc = nn.Linear(768, num_classes)
self.fc.stddev = 0.001
def forward(self, x):
# 17 x 17 x 768
x = F.avg_pool2d(x, kernel_size=5, stride=3)
# 5 x 5 x 768
x = self.conv0(x)
# 5 x 5 x 128
x = self.conv1(x)
# 1 x 1 x 768
x = x.view(x.size(0), -1)
# 768
x = self.fc(x)
# 1000
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, bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
return F.relu(x, inplace=True)
class InceptionV3(nn.Module):
def __init__(self, num_classes=1000, aux_logits=False, transform_input=False):
super(InceptionV3, self).__init__()
self.aux_logits = aux_logits
self.transform_input = transform_input
self.Conv2d_1a_3x3 = BasicConv2d(3, 32, kernel_size=3, stride=2)
self.Conv2d_2a_3x3 = BasicConv2d(32, 32, kernel_size=3)
self.Conv2d_2b_3x3 = BasicConv2d(32, 64, kernel_size=3, padding=1)
self.Conv2d_3b_1x1 = BasicConv2d(64, 80, kernel_size=1)
self.Conv2d_4a_3x3 = BasicConv2d(80, 192, kernel_size=3)
self.Mixed_5b = InceptionA(192, pool_features=32)
self.Mixed_5c = InceptionA(256, pool_features=64)
self.Mixed_5d = InceptionA(288, pool_features=64)
self.Mixed_6a = ReductionA(288)
self.Mixed_6b = InceptionB(768, channels_7x7=128)
self.Mixed_6c = InceptionB(768, channels_7x7=160)
self.Mixed_6d = InceptionB(768, channels_7x7=160)
self.Mixed_6e = InceptionB(768, channels_7x7=192)
if aux_logits:
self.AuxLogits = InceptionAux(768, num_classes)
self.Mixed_7a = ReductionB(768)
self.Mixed_7b = InceptionC(1280)
self.Mixed_7c = InceptionC(2048)
self.fc = nn.Linear(2048, num_classes)
def forward(self, x):
if self.transform_input: # 1
x = x.clone()
x[:, 0] = x[:, 0] * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
x[:, 1] = x[:, 1] * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
x[:, 2] = x[:, 2] * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
# 299 x 299 x 3
x = self.Conv2d_1a_3x3(x)
# 149 x 149 x 32
x = self.Conv2d_2a_3x3(x)
# 147 x 147 x 32
x = self.Conv2d_2b_3x3(x)
# 147 x 147 x 64
x = F.max_pool2d(x, kernel_size=3, stride=2)
# 73 x 73 x 64
x = self.Conv2d_3b_1x1(x)
# 73 x 73 x 80
x = self.Conv2d_4a_3x3(x)
# 71 x 71 x 192
x = F.max_pool2d(x, kernel_size=3, stride=2)
# 35 x 35 x 192
x = self.Mixed_5b(x)
# 35 x 35 x 256
x = self.Mixed_5c(x)
# 35 x 35 x 288
x = self.Mixed_5d(x)
# 35 x 35 x 288
x = self.Mixed_6a(x)
# 17 x 17 x 768
x = self.Mixed_6b(x)
# 17 x 17 x 768
x = self.Mixed_6c(x)
# 17 x 17 x 768
x = self.Mixed_6d(x)
# 17 x 17 x 768
x = self.Mixed_6e(x)
# 17 x 17 x 768
if self.training and self.aux_logits:
aux = self.AuxLogits(x)
# 17 x 17 x 768
x = self.Mixed_7a(x)
# 8 x 8 x 1280
x = self.Mixed_7b(x)
# 8 x 8 x 2048
x = self.Mixed_7c(x)
# 8 x 8 x 2048
x = F.avg_pool2d(x, kernel_size=8)
# 1 x 1 x 2048
x = F.dropout(x, training=self.training)
# 1 x 1 x 2048
x = x.view(x.size(0), -1)
# 2048
x = self.fc(x)
# 1000 (num_classes)
if self.training and self.aux_logits:
return x, aux
return x
model = InceptionV3(num_classes=len(classNames)).to(device)
model
InceptionV3(
(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)
)
(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)
)
(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): ReductionA(
(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): InceptionB(
(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): InceptionB(
(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): InceptionB(
(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): InceptionB(
(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)
)
)
(Mixed_7a): ReductionB(
(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): InceptionC(
(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): InceptionC(
(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)
)
)
(fc): Linear(in_features=2048, out_features=4, bias=True)
)
# 查看模型详情
import torchsummary as summary
summary.summary(model,(3,299,299))
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 149, 149] 864
BatchNorm2d-2 [-1, 32, 149, 149] 64
BasicConv2d-3 [-1, 32, 149, 149] 0
Conv2d-4 [-1, 32, 147, 147] 9,216
BatchNorm2d-5 [-1, 32, 147, 147] 64
BasicConv2d-6 [-1, 32, 147, 147] 0
Conv2d-7 [-1, 64, 147, 147] 18,432
BatchNorm2d-8 [-1, 64, 147, 147] 128
BasicConv2d-9 [-1, 64, 147, 147] 0
Conv2d-10 [-1, 80, 73, 73] 5,120
BatchNorm2d-11 [-1, 80, 73, 73] 160
BasicConv2d-12 [-1, 80, 73, 73] 0
Conv2d-13 [-1, 192, 71, 71] 138,240
BatchNorm2d-14 [-1, 192, 71, 71] 384
BasicConv2d-15 [-1, 192, 71, 71] 0
Conv2d-16 [-1, 64, 35, 35] 12,288
BatchNorm2d-17 [-1, 64, 35, 35] 128
BasicConv2d-18 [-1, 64, 35, 35] 0
Conv2d-19 [-1, 48, 35, 35] 9,216
BatchNorm2d-20 [-1, 48, 35, 35] 96
BasicConv2d-21 [-1, 48, 35, 35] 0
Conv2d-22 [-1, 64, 35, 35] 76,800
BatchNorm2d-23 [-1, 64, 35, 35] 128
BasicConv2d-24 [-1, 64, 35, 35] 0
Conv2d-25 [-1, 64, 35, 35] 12,288
BatchNorm2d-26 [-1, 64, 35, 35] 128
BasicConv2d-27 [-1, 64, 35, 35] 0
Conv2d-28 [-1, 96, 35, 35] 55,296
BatchNorm2d-29 [-1, 96, 35, 35] 192
BasicConv2d-30 [-1, 96, 35, 35] 0
Conv2d-31 [-1, 96, 35, 35] 82,944
BatchNorm2d-32 [-1, 96, 35, 35] 192
BasicConv2d-33 [-1, 96, 35, 35] 0
Conv2d-34 [-1, 32, 35, 35] 6,144
BatchNorm2d-35 [-1, 32, 35, 35] 64
BasicConv2d-36 [-1, 32, 35, 35] 0
InceptionA-37 [-1, 256, 35, 35] 0
Conv2d-38 [-1, 64, 35, 35] 16,384
BatchNorm2d-39 [-1, 64, 35, 35] 128
BasicConv2d-40 [-1, 64, 35, 35] 0
Conv2d-41 [-1, 48, 35, 35] 12,288
BatchNorm2d-42 [-1, 48, 35, 35] 96
BasicConv2d-43 [-1, 48, 35, 35] 0
Conv2d-44 [-1, 64, 35, 35] 76,800
BatchNorm2d-45 [-1, 64, 35, 35] 128
BasicConv2d-46 [-1, 64, 35, 35] 0
Conv2d-47 [-1, 64, 35, 35] 16,384
BatchNorm2d-48 [-1, 64, 35, 35] 128
BasicConv2d-49 [-1, 64, 35, 35] 0
Conv2d-50 [-1, 96, 35, 35] 55,296
BatchNorm2d-51 [-1, 96, 35, 35] 192
BasicConv2d-52 [-1, 96, 35, 35] 0
Conv2d-53 [-1, 96, 35, 35] 82,944
BatchNorm2d-54 [-1, 96, 35, 35] 192
BasicConv2d-55 [-1, 96, 35, 35] 0
Conv2d-56 [-1, 64, 35, 35] 16,384
BatchNorm2d-57 [-1, 64, 35, 35] 128
BasicConv2d-58 [-1, 64, 35, 35] 0
InceptionA-59 [-1, 288, 35, 35] 0
Conv2d-60 [-1, 64, 35, 35] 18,432
BatchNorm2d-61 [-1, 64, 35, 35] 128
BasicConv2d-62 [-1, 64, 35, 35] 0
Conv2d-63 [-1, 48, 35, 35] 13,824
BatchNorm2d-64 [-1, 48, 35, 35] 96
BasicConv2d-65 [-1, 48, 35, 35] 0
Conv2d-66 [-1, 64, 35, 35] 76,800
BatchNorm2d-67 [-1, 64, 35, 35] 128
BasicConv2d-68 [-1, 64, 35, 35] 0
Conv2d-69 [-1, 64, 35, 35] 18,432
BatchNorm2d-70 [-1, 64, 35, 35] 128
BasicConv2d-71 [-1, 64, 35, 35] 0
Conv2d-72 [-1, 96, 35, 35] 55,296
BatchNorm2d-73 [-1, 96, 35, 35] 192
BasicConv2d-74 [-1, 96, 35, 35] 0
Conv2d-75 [-1, 96, 35, 35] 82,944
BatchNorm2d-76 [-1, 96, 35, 35] 192
BasicConv2d-77 [-1, 96, 35, 35] 0
Conv2d-78 [-1, 64, 35, 35] 18,432
BatchNorm2d-79 [-1, 64, 35, 35] 128
BasicConv2d-80 [-1, 64, 35, 35] 0
InceptionA-81 [-1, 288, 35, 35] 0
Conv2d-82 [-1, 384, 17, 17] 995,328
BatchNorm2d-83 [-1, 384, 17, 17] 768
BasicConv2d-84 [-1, 384, 17, 17] 0
Conv2d-85 [-1, 64, 35, 35] 18,432
BatchNorm2d-86 [-1, 64, 35, 35] 128
BasicConv2d-87 [-1, 64, 35, 35] 0
Conv2d-88 [-1, 96, 35, 35] 55,296
BatchNorm2d-89 [-1, 96, 35, 35] 192
BasicConv2d-90 [-1, 96, 35, 35] 0
Conv2d-91 [-1, 96, 17, 17] 82,944
BatchNorm2d-92 [-1, 96, 17, 17] 192
BasicConv2d-93 [-1, 96, 17, 17] 0
ReductionA-94 [-1, 768, 17, 17] 0
Conv2d-95 [-1, 192, 17, 17] 147,456
BatchNorm2d-96 [-1, 192, 17, 17] 384
BasicConv2d-97 [-1, 192, 17, 17] 0
Conv2d-98 [-1, 128, 17, 17] 98,304
BatchNorm2d-99 [-1, 128, 17, 17] 256
BasicConv2d-100 [-1, 128, 17, 17] 0
Conv2d-101 [-1, 128, 17, 17] 114,688
BatchNorm2d-102 [-1, 128, 17, 17] 256
BasicConv2d-103 [-1, 128, 17, 17] 0
Conv2d-104 [-1, 192, 17, 17] 172,032
BatchNorm2d-105 [-1, 192, 17, 17] 384
BasicConv2d-106 [-1, 192, 17, 17] 0
Conv2d-107 [-1, 128, 17, 17] 98,304
BatchNorm2d-108 [-1, 128, 17, 17] 256
BasicConv2d-109 [-1, 128, 17, 17] 0
Conv2d-110 [-1, 128, 17, 17] 114,688
BatchNorm2d-111 [-1, 128, 17, 17] 256
BasicConv2d-112 [-1, 128, 17, 17] 0
Conv2d-113 [-1, 128, 17, 17] 114,688
BatchNorm2d-114 [-1, 128, 17, 17] 256
BasicConv2d-115 [-1, 128, 17, 17] 0
Conv2d-116 [-1, 128, 17, 17] 114,688
BatchNorm2d-117 [-1, 128, 17, 17] 256
BasicConv2d-118 [-1, 128, 17, 17] 0
Conv2d-119 [-1, 192, 17, 17] 172,032
BatchNorm2d-120 [-1, 192, 17, 17] 384
BasicConv2d-121 [-1, 192, 17, 17] 0
Conv2d-122 [-1, 192, 17, 17] 147,456
BatchNorm2d-123 [-1, 192, 17, 17] 384
BasicConv2d-124 [-1, 192, 17, 17] 0
InceptionB-125 [-1, 768, 17, 17] 0
Conv2d-126 [-1, 192, 17, 17] 147,456
BatchNorm2d-127 [-1, 192, 17, 17] 384
BasicConv2d-128 [-1, 192, 17, 17] 0
Conv2d-129 [-1, 160, 17, 17] 122,880
BatchNorm2d-130 [-1, 160, 17, 17] 320
BasicConv2d-131 [-1, 160, 17, 17] 0
Conv2d-132 [-1, 160, 17, 17] 179,200
BatchNorm2d-133 [-1, 160, 17, 17] 320
BasicConv2d-134 [-1, 160, 17, 17] 0
Conv2d-135 [-1, 192, 17, 17] 215,040
BatchNorm2d-136 [-1, 192, 17, 17] 384
BasicConv2d-137 [-1, 192, 17, 17] 0
Conv2d-138 [-1, 160, 17, 17] 122,880
BatchNorm2d-139 [-1, 160, 17, 17] 320
BasicConv2d-140 [-1, 160, 17, 17] 0
Conv2d-141 [-1, 160, 17, 17] 179,200
BatchNorm2d-142 [-1, 160, 17, 17] 320
BasicConv2d-143 [-1, 160, 17, 17] 0
Conv2d-144 [-1, 160, 17, 17] 179,200
BatchNorm2d-145 [-1, 160, 17, 17] 320
BasicConv2d-146 [-1, 160, 17, 17] 0
Conv2d-147 [-1, 160, 17, 17] 179,200
BatchNorm2d-148 [-1, 160, 17, 17] 320
BasicConv2d-149 [-1, 160, 17, 17] 0
Conv2d-150 [-1, 192, 17, 17] 215,040
BatchNorm2d-151 [-1, 192, 17, 17] 384
BasicConv2d-152 [-1, 192, 17, 17] 0
Conv2d-153 [-1, 192, 17, 17] 147,456
BatchNorm2d-154 [-1, 192, 17, 17] 384
BasicConv2d-155 [-1, 192, 17, 17] 0
InceptionB-156 [-1, 768, 17, 17] 0
Conv2d-157 [-1, 192, 17, 17] 147,456
BatchNorm2d-158 [-1, 192, 17, 17] 384
BasicConv2d-159 [-1, 192, 17, 17] 0
Conv2d-160 [-1, 160, 17, 17] 122,880
BatchNorm2d-161 [-1, 160, 17, 17] 320
BasicConv2d-162 [-1, 160, 17, 17] 0
Conv2d-163 [-1, 160, 17, 17] 179,200
BatchNorm2d-164 [-1, 160, 17, 17] 320
BasicConv2d-165 [-1, 160, 17, 17] 0
Conv2d-166 [-1, 192, 17, 17] 215,040
BatchNorm2d-167 [-1, 192, 17, 17] 384
BasicConv2d-168 [-1, 192, 17, 17] 0
Conv2d-169 [-1, 160, 17, 17] 122,880
BatchNorm2d-170 [-1, 160, 17, 17] 320
BasicConv2d-171 [-1, 160, 17, 17] 0
Conv2d-172 [-1, 160, 17, 17] 179,200
BatchNorm2d-173 [-1, 160, 17, 17] 320
BasicConv2d-174 [-1, 160, 17, 17] 0
Conv2d-175 [-1, 160, 17, 17] 179,200
BatchNorm2d-176 [-1, 160, 17, 17] 320
BasicConv2d-177 [-1, 160, 17, 17] 0
Conv2d-178 [-1, 160, 17, 17] 179,200
BatchNorm2d-179 [-1, 160, 17, 17] 320
BasicConv2d-180 [-1, 160, 17, 17] 0
Conv2d-181 [-1, 192, 17, 17] 215,040
BatchNorm2d-182 [-1, 192, 17, 17] 384
BasicConv2d-183 [-1, 192, 17, 17] 0
Conv2d-184 [-1, 192, 17, 17] 147,456
BatchNorm2d-185 [-1, 192, 17, 17] 384
BasicConv2d-186 [-1, 192, 17, 17] 0
InceptionB-187 [-1, 768, 17, 17] 0
Conv2d-188 [-1, 192, 17, 17] 147,456
BatchNorm2d-189 [-1, 192, 17, 17] 384
BasicConv2d-190 [-1, 192, 17, 17] 0
Conv2d-191 [-1, 192, 17, 17] 147,456
BatchNorm2d-192 [-1, 192, 17, 17] 384
BasicConv2d-193 [-1, 192, 17, 17] 0
Conv2d-194 [-1, 192, 17, 17] 258,048
BatchNorm2d-195 [-1, 192, 17, 17] 384
BasicConv2d-196 [-1, 192, 17, 17] 0
Conv2d-197 [-1, 192, 17, 17] 258,048
BatchNorm2d-198 [-1, 192, 17, 17] 384
BasicConv2d-199 [-1, 192, 17, 17] 0
Conv2d-200 [-1, 192, 17, 17] 147,456
BatchNorm2d-201 [-1, 192, 17, 17] 384
BasicConv2d-202 [-1, 192, 17, 17] 0
Conv2d-203 [-1, 192, 17, 17] 258,048
BatchNorm2d-204 [-1, 192, 17, 17] 384
BasicConv2d-205 [-1, 192, 17, 17] 0
Conv2d-206 [-1, 192, 17, 17] 258,048
BatchNorm2d-207 [-1, 192, 17, 17] 384
BasicConv2d-208 [-1, 192, 17, 17] 0
Conv2d-209 [-1, 192, 17, 17] 258,048
BatchNorm2d-210 [-1, 192, 17, 17] 384
BasicConv2d-211 [-1, 192, 17, 17] 0
Conv2d-212 [-1, 192, 17, 17] 258,048
BatchNorm2d-213 [-1, 192, 17, 17] 384
BasicConv2d-214 [-1, 192, 17, 17] 0
Conv2d-215 [-1, 192, 17, 17] 147,456
BatchNorm2d-216 [-1, 192, 17, 17] 384
BasicConv2d-217 [-1, 192, 17, 17] 0
InceptionB-218 [-1, 768, 17, 17] 0
Conv2d-219 [-1, 192, 17, 17] 147,456
BatchNorm2d-220 [-1, 192, 17, 17] 384
BasicConv2d-221 [-1, 192, 17, 17] 0
Conv2d-222 [-1, 320, 8, 8] 552,960
BatchNorm2d-223 [-1, 320, 8, 8] 640
BasicConv2d-224 [-1, 320, 8, 8] 0
Conv2d-225 [-1, 192, 17, 17] 147,456
BatchNorm2d-226 [-1, 192, 17, 17] 384
BasicConv2d-227 [-1, 192, 17, 17] 0
Conv2d-228 [-1, 192, 17, 17] 258,048
BatchNorm2d-229 [-1, 192, 17, 17] 384
BasicConv2d-230 [-1, 192, 17, 17] 0
Conv2d-231 [-1, 192, 17, 17] 258,048
BatchNorm2d-232 [-1, 192, 17, 17] 384
BasicConv2d-233 [-1, 192, 17, 17] 0
Conv2d-234 [-1, 192, 8, 8] 331,776
BatchNorm2d-235 [-1, 192, 8, 8] 384
BasicConv2d-236 [-1, 192, 8, 8] 0
ReductionB-237 [-1, 1280, 8, 8] 0
Conv2d-238 [-1, 320, 8, 8] 409,600
BatchNorm2d-239 [-1, 320, 8, 8] 640
BasicConv2d-240 [-1, 320, 8, 8] 0
Conv2d-241 [-1, 384, 8, 8] 491,520
BatchNorm2d-242 [-1, 384, 8, 8] 768
BasicConv2d-243 [-1, 384, 8, 8] 0
Conv2d-244 [-1, 384, 8, 8] 442,368
BatchNorm2d-245 [-1, 384, 8, 8] 768
BasicConv2d-246 [-1, 384, 8, 8] 0
Conv2d-247 [-1, 384, 8, 8] 442,368
BatchNorm2d-248 [-1, 384, 8, 8] 768
BasicConv2d-249 [-1, 384, 8, 8] 0
Conv2d-250 [-1, 448, 8, 8] 573,440
BatchNorm2d-251 [-1, 448, 8, 8] 896
BasicConv2d-252 [-1, 448, 8, 8] 0
Conv2d-253 [-1, 384, 8, 8] 1,548,288
BatchNorm2d-254 [-1, 384, 8, 8] 768
BasicConv2d-255 [-1, 384, 8, 8] 0
Conv2d-256 [-1, 384, 8, 8] 442,368
BatchNorm2d-257 [-1, 384, 8, 8] 768
BasicConv2d-258 [-1, 384, 8, 8] 0
Conv2d-259 [-1, 384, 8, 8] 442,368
BatchNorm2d-260 [-1, 384, 8, 8] 768
BasicConv2d-261 [-1, 384, 8, 8] 0
Conv2d-262 [-1, 192, 8, 8] 245,760
BatchNorm2d-263 [-1, 192, 8, 8] 384
BasicConv2d-264 [-1, 192, 8, 8] 0
InceptionC-265 [-1, 2048, 8, 8] 0
Conv2d-266 [-1, 320, 8, 8] 655,360
BatchNorm2d-267 [-1, 320, 8, 8] 640
BasicConv2d-268 [-1, 320, 8, 8] 0
Conv2d-269 [-1, 384, 8, 8] 786,432
BatchNorm2d-270 [-1, 384, 8, 8] 768
BasicConv2d-271 [-1, 384, 8, 8] 0
Conv2d-272 [-1, 384, 8, 8] 442,368
BatchNorm2d-273 [-1, 384, 8, 8] 768
BasicConv2d-274 [-1, 384, 8, 8] 0
Conv2d-275 [-1, 384, 8, 8] 442,368
BatchNorm2d-276 [-1, 384, 8, 8] 768
BasicConv2d-277 [-1, 384, 8, 8] 0
Conv2d-278 [-1, 448, 8, 8] 917,504
BatchNorm2d-279 [-1, 448, 8, 8] 896
BasicConv2d-280 [-1, 448, 8, 8] 0
Conv2d-281 [-1, 384, 8, 8] 1,548,288
BatchNorm2d-282 [-1, 384, 8, 8] 768
BasicConv2d-283 [-1, 384, 8, 8] 0
Conv2d-284 [-1, 384, 8, 8] 442,368
BatchNorm2d-285 [-1, 384, 8, 8] 768
BasicConv2d-286 [-1, 384, 8, 8] 0
Conv2d-287 [-1, 384, 8, 8] 442,368
BatchNorm2d-288 [-1, 384, 8, 8] 768
BasicConv2d-289 [-1, 384, 8, 8] 0
Conv2d-290 [-1, 192, 8, 8] 393,216
BatchNorm2d-291 [-1, 192, 8, 8] 384
BasicConv2d-292 [-1, 192, 8, 8] 0
InceptionC-293 [-1, 2048, 8, 8] 0
Linear-294 [-1, 4] 8,196
================================================================
Total params: 21,793,764
Trainable params: 21,793,764
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 1.02
Forward/backward pass size (MB): 224.12
Params size (MB): 83.14
Estimated Total Size (MB): 308.28
----------------------------------------------------------------
5. 设置超参数：定义损失函数，学习率，以及根据学习率定义优化器等
# loss_fn = nn.CrossEntropyLoss() # 创建损失函数
# learn_rate = 1e-3 # 初始学习率
# def adjust_learning_rate(optimizer,epoch,start_lr):
# # 每两个epoch 衰减到原来的0.98
# lr = start_lr * (0.92 ** (epoch//2))
# for param_group in optimizer.param_groups:
# param_group['lr'] = lr
# optimizer = torch.optim.Adam(model.parameters(),lr=learn_rate)
# 调用官方接口示例
loss_fn = nn.CrossEntropyLoss()
# learn_rate = 1e-4
learn_rate = 3e-4
lambda1 = lambda epoch:(0.92**(epoch//2))
optimizer = torch.optim.Adam(model.parameters(),lr = learn_rate)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer,lr_lambda=lambda1) # 选定调整方法
6. 训练函数
# 训练函数
def train(dataloader,model,loss_fn,optimizer):
size = len(dataloader.dataset) # 训练集大小
num_batches = len(dataloader) # 批次数目
train_loss,train_acc = 0,0
for X,y in dataloader:
X,y = X.to(device),y.to(device)
# 计算预测误差
pred = model(X)
loss = loss_fn(pred,y)
# 反向传播
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 记录acc与loss
train_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc,train_loss
7. 测试函数
# 测试函数
def test(dataloader,model,loss_fn):
size = len(dataloader.dataset)
num_batches = len(dataloader)
test_acc,test_loss = 0,0
with torch.no_grad():
for X,y in dataloader:
X,y = X.to(device),y.to(device)
# 计算loss
pred = model(X)
loss = loss_fn(pred,y)
test_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
test_loss += loss.item()
test_acc /= size
test_loss /= num_batches
return test_acc,test_loss
8. 正式训练
import copy
epochs = 60
train_acc = []
train_loss = []
test_acc = []
test_loss = []
best_acc = 0.0
# 检查 GPU 可用性并打印设备信息
if torch.cuda.is_available():
for i in range(torch.cuda.device_count()):
print(f"GPU {i}: {torch.cuda.get_device_name(i)}")
print(f"Initial Memory Allocated: {torch.cuda.memory_allocated(i)/1024**2:.2f} MB")
print(f"Initial Memory Cached: {torch.cuda.memory_reserved(i)/1024**2:.2f} MB")
else:
print("No GPU available. Using CPU.")
# 多显卡设置 当前使用的是使用 PyTorch 自带的 DataParallel，后续如有需要可以设置为DistributedDataParallel，这是更加高效的方式
# 且多卡不一定比单卡效果就好，需要调整优化
# if torch.cuda.device_count() > 1:
# print(f"Using {torch.cuda.device_count()} GPUs")
# model = nn.DataParallel(model)
# model = model.to('cuda')
for epoch in range(epochs):
# 更新学习率——使用自定义学习率时使用
# adjust_learning_rate(optimizer,epoch,learn_rate)
model.train()
epoch_train_acc,epoch_train_loss = train(train_dl,model,loss_fn,optimizer)
scheduler.step() # 更新学习率——调用官方动态学习率时使用
model.eval()
epoch_test_acc,epoch_test_loss = test(test_dl,model,loss_fn)
# 保存最佳模型到 best_model
if epoch_test_acc > best_acc:
best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d},Train_acc:{:.1f}%,Train_loss:{:.3f},Test_acc:{:.1f}%,Test_loss:{:.3f},Lr:{:.2E}')
print(template.format(epoch+1,epoch_train_acc*100,epoch_train_loss,epoch_test_acc*100,epoch_test_loss,lr))
# 实时监控 GPU 状态
if torch.cuda.is_available():
for i in range(torch.cuda.device_count()):
print(f"GPU {i} Usage:")
print(f" Memory Allocated: {torch.cuda.memory_allocated(i)/1024**2:.2f} MB")
print(f" Memory Cached: {torch.cuda.memory_reserved(i)/1024**2:.2f} MB")
print(f" Max Memory Allocated: {torch.cuda.max_memory_allocated(i)/1024**2:.2f} MB")
print(f" Max Memory Cached: {torch.cuda.max_memory_reserved(i)/1024**2:.2f} MB")
print('Done','best_acc: ',best_acc)
GPU 0: NVIDIA GeForce RTX 4070 Laptop GPU
Initial Memory Allocated: 92.00 MB
Initial Memory Cached: 524.00 MB
Epoch: 1,Train_acc:75.0%,Train_loss:0.664,Test_acc:35.6%,Test_loss:3.178,Lr:3.00E-04
GPU 0 Usage:
Memory Allocated: 442.28 MB
Memory Cached: 4330.00 MB
Max Memory Allocated: 3518.43 MB
Max Memory Cached: 4330.00 MB
Epoch: 2,Train_acc:85.4%,Train_loss:0.473,Test_acc:75.6%,Test_loss:1.198,Lr:2.76E-04
GPU 0 Usage:
Memory Allocated: 441.65 MB
Memory Cached: 4366.00 MB
Max Memory Allocated: 3601.60 MB
Max Memory Cached: 4366.00 MB
Epoch: 3,Train_acc:84.9%,Train_loss:0.458,Test_acc:87.6%,Test_loss:0.368,Lr:2.76E-04
GPU 0 Usage:
Memory Allocated: 442.17 MB
Memory Cached: 4366.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4366.00 MB
Epoch: 4,Train_acc:86.0%,Train_loss:0.446,Test_acc:87.1%,Test_loss:0.414,Lr:2.54E-04
GPU 0 Usage:
Memory Allocated: 443.47 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch: 5,Train_acc:89.0%,Train_loss:0.383,Test_acc:89.3%,Test_loss:0.277,Lr:2.54E-04
GPU 0 Usage:
Memory Allocated: 440.66 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch: 6,Train_acc:87.6%,Train_loss:0.382,Test_acc:88.4%,Test_loss:0.378,Lr:2.34E-04
GPU 0 Usage:
Memory Allocated: 438.65 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch: 7,Train_acc:87.6%,Train_loss:0.389,Test_acc:87.6%,Test_loss:0.297,Lr:2.34E-04
GPU 0 Usage:
Memory Allocated: 440.96 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch: 8,Train_acc:89.2%,Train_loss:0.325,Test_acc:88.4%,Test_loss:0.267,Lr:2.15E-04
GPU 0 Usage:
Memory Allocated: 441.04 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch: 9,Train_acc:89.1%,Train_loss:0.341,Test_acc:87.6%,Test_loss:0.309,Lr:2.15E-04
GPU 0 Usage:
Memory Allocated: 441.02 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:10,Train_acc:88.7%,Train_loss:0.340,Test_acc:92.4%,Test_loss:0.233,Lr:1.98E-04
GPU 0 Usage:
Memory Allocated: 439.24 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:11,Train_acc:89.9%,Train_loss:0.307,Test_acc:90.2%,Test_loss:0.254,Lr:1.98E-04
GPU 0 Usage:
Memory Allocated: 440.40 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:12,Train_acc:89.0%,Train_loss:0.322,Test_acc:91.6%,Test_loss:0.250,Lr:1.82E-04
GPU 0 Usage:
Memory Allocated: 442.53 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:13,Train_acc:92.7%,Train_loss:0.242,Test_acc:92.0%,Test_loss:0.223,Lr:1.82E-04
GPU 0 Usage:
Memory Allocated: 441.67 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:14,Train_acc:91.1%,Train_loss:0.311,Test_acc:91.1%,Test_loss:0.224,Lr:1.67E-04
GPU 0 Usage:
Memory Allocated: 440.82 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:15,Train_acc:90.1%,Train_loss:0.300,Test_acc:93.3%,Test_loss:0.196,Lr:1.67E-04
GPU 0 Usage:
Memory Allocated: 442.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:16,Train_acc:89.1%,Train_loss:0.334,Test_acc:89.3%,Test_loss:0.333,Lr:1.54E-04
GPU 0 Usage:
Memory Allocated: 440.50 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:17,Train_acc:89.7%,Train_loss:0.335,Test_acc:89.8%,Test_loss:0.232,Lr:1.54E-04
GPU 0 Usage:
Memory Allocated: 441.43 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:18,Train_acc:93.1%,Train_loss:0.260,Test_acc:90.7%,Test_loss:0.260,Lr:1.42E-04
GPU 0 Usage:
Memory Allocated: 441.24 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:19,Train_acc:91.3%,Train_loss:0.231,Test_acc:92.0%,Test_loss:0.179,Lr:1.42E-04
GPU 0 Usage:
Memory Allocated: 441.50 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:20,Train_acc:90.4%,Train_loss:0.238,Test_acc:92.4%,Test_loss:0.656,Lr:1.30E-04
GPU 0 Usage:
Memory Allocated: 440.64 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:21,Train_acc:93.3%,Train_loss:0.195,Test_acc:92.9%,Test_loss:0.189,Lr:1.30E-04
GPU 0 Usage:
Memory Allocated: 441.06 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:22,Train_acc:93.7%,Train_loss:0.261,Test_acc:91.1%,Test_loss:0.206,Lr:1.20E-04
GPU 0 Usage:
Memory Allocated: 441.77 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:23,Train_acc:94.2%,Train_loss:0.195,Test_acc:92.4%,Test_loss:0.205,Lr:1.20E-04
GPU 0 Usage:
Memory Allocated: 441.27 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:24,Train_acc:91.9%,Train_loss:0.236,Test_acc:93.8%,Test_loss:0.186,Lr:1.10E-04
GPU 0 Usage:
Memory Allocated: 443.12 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:25,Train_acc:93.4%,Train_loss:0.309,Test_acc:94.2%,Test_loss:0.149,Lr:1.10E-04
GPU 0 Usage:
Memory Allocated: 443.39 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3602.83 MB
Max Memory Cached: 4368.00 MB
Epoch:26,Train_acc:93.2%,Train_loss:0.177,Test_acc:92.4%,Test_loss:0.192,Lr:1.01E-04
GPU 0 Usage:
Memory Allocated: 441.71 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.01 MB
Max Memory Cached: 4368.00 MB
Epoch:27,Train_acc:94.9%,Train_loss:0.222,Test_acc:92.0%,Test_loss:0.227,Lr:1.01E-04
GPU 0 Usage:
Memory Allocated: 443.70 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.28 MB
Max Memory Cached: 4368.00 MB
Epoch:28,Train_acc:93.8%,Train_loss:0.200,Test_acc:94.2%,Test_loss:0.144,Lr:9.34E-05
GPU 0 Usage:
Memory Allocated: 441.37 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.28 MB
Max Memory Cached: 4368.00 MB
Epoch:29,Train_acc:94.9%,Train_loss:0.158,Test_acc:92.4%,Test_loss:0.168,Lr:9.34E-05
GPU 0 Usage:
Memory Allocated: 441.79 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.28 MB
Max Memory Cached: 4368.00 MB
Epoch:30,Train_acc:95.7%,Train_loss:0.151,Test_acc:93.3%,Test_loss:0.161,Lr:8.59E-05
GPU 0 Usage:
Memory Allocated: 442.08 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:31,Train_acc:94.7%,Train_loss:0.137,Test_acc:94.2%,Test_loss:0.136,Lr:8.59E-05
GPU 0 Usage:
Memory Allocated: 441.25 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:32,Train_acc:95.9%,Train_loss:0.133,Test_acc:94.2%,Test_loss:0.197,Lr:7.90E-05
GPU 0 Usage:
Memory Allocated: 442.79 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:33,Train_acc:94.7%,Train_loss:0.144,Test_acc:94.2%,Test_loss:0.366,Lr:7.90E-05
GPU 0 Usage:
Memory Allocated: 442.73 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:34,Train_acc:96.2%,Train_loss:0.109,Test_acc:92.0%,Test_loss:0.248,Lr:7.27E-05
GPU 0 Usage:
Memory Allocated: 442.30 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:35,Train_acc:96.0%,Train_loss:0.138,Test_acc:92.9%,Test_loss:0.177,Lr:7.27E-05
GPU 0 Usage:
Memory Allocated: 440.91 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:36,Train_acc:96.7%,Train_loss:0.179,Test_acc:92.4%,Test_loss:0.206,Lr:6.69E-05
GPU 0 Usage:
Memory Allocated: 441.46 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:37,Train_acc:95.2%,Train_loss:0.148,Test_acc:91.1%,Test_loss:0.219,Lr:6.69E-05
GPU 0 Usage:
Memory Allocated: 440.19 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:38,Train_acc:94.0%,Train_loss:0.162,Test_acc:93.3%,Test_loss:0.157,Lr:6.15E-05
GPU 0 Usage:
Memory Allocated: 443.07 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:39,Train_acc:97.4%,Train_loss:0.117,Test_acc:92.9%,Test_loss:0.279,Lr:6.15E-05
GPU 0 Usage:
Memory Allocated: 442.75 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:40,Train_acc:95.0%,Train_loss:0.203,Test_acc:92.0%,Test_loss:0.590,Lr:5.66E-05
GPU 0 Usage:
Memory Allocated: 442.67 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:41,Train_acc:96.2%,Train_loss:0.127,Test_acc:93.3%,Test_loss:0.199,Lr:5.66E-05
GPU 0 Usage:
Memory Allocated: 442.07 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:42,Train_acc:96.2%,Train_loss:0.110,Test_acc:96.0%,Test_loss:0.132,Lr:5.21E-05
GPU 0 Usage:
Memory Allocated: 441.30 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:43,Train_acc:97.3%,Train_loss:0.132,Test_acc:94.2%,Test_loss:0.175,Lr:5.21E-05
GPU 0 Usage:
Memory Allocated: 442.24 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:44,Train_acc:96.0%,Train_loss:0.111,Test_acc:93.3%,Test_loss:0.179,Lr:4.79E-05
GPU 0 Usage:
Memory Allocated: 440.67 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:45,Train_acc:97.8%,Train_loss:0.065,Test_acc:93.8%,Test_loss:0.175,Lr:4.79E-05
GPU 0 Usage:
Memory Allocated: 441.61 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:46,Train_acc:97.7%,Train_loss:0.078,Test_acc:92.9%,Test_loss:0.188,Lr:4.41E-05
GPU 0 Usage:
Memory Allocated: 441.65 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:47,Train_acc:97.3%,Train_loss:0.090,Test_acc:92.4%,Test_loss:0.183,Lr:4.41E-05
GPU 0 Usage:
Memory Allocated: 441.28 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:48,Train_acc:98.1%,Train_loss:0.065,Test_acc:95.1%,Test_loss:0.110,Lr:4.06E-05
GPU 0 Usage:
Memory Allocated: 441.88 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:49,Train_acc:97.8%,Train_loss:0.068,Test_acc:92.9%,Test_loss:0.181,Lr:4.06E-05
GPU 0 Usage:
Memory Allocated: 442.35 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:50,Train_acc:98.7%,Train_loss:0.061,Test_acc:94.2%,Test_loss:0.153,Lr:3.73E-05
GPU 0 Usage:
Memory Allocated: 441.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:51,Train_acc:98.3%,Train_loss:0.149,Test_acc:92.0%,Test_loss:0.185,Lr:3.73E-05
GPU 0 Usage:
Memory Allocated: 442.35 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:52,Train_acc:97.8%,Train_loss:0.067,Test_acc:90.7%,Test_loss:0.237,Lr:3.43E-05
GPU 0 Usage:
Memory Allocated: 441.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:53,Train_acc:98.3%,Train_loss:0.056,Test_acc:93.3%,Test_loss:0.158,Lr:3.43E-05
GPU 0 Usage:
Memory Allocated: 442.35 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:54,Train_acc:99.0%,Train_loss:0.101,Test_acc:95.6%,Test_loss:0.151,Lr:3.16E-05
GPU 0 Usage:
Memory Allocated: 441.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:55,Train_acc:98.4%,Train_loss:0.111,Test_acc:94.2%,Test_loss:0.155,Lr:3.16E-05
GPU 0 Usage:
Memory Allocated: 442.35 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:56,Train_acc:98.1%,Train_loss:0.065,Test_acc:94.7%,Test_loss:0.133,Lr:2.91E-05
GPU 0 Usage:
Memory Allocated: 441.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:57,Train_acc:97.0%,Train_loss:0.137,Test_acc:94.7%,Test_loss:0.141,Lr:2.91E-05
GPU 0 Usage:
Memory Allocated: 442.35 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:58,Train_acc:98.6%,Train_loss:0.054,Test_acc:92.4%,Test_loss:0.171,Lr:2.67E-05
GPU 0 Usage:
Memory Allocated: 441.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:59,Train_acc:98.7%,Train_loss:0.043,Test_acc:95.1%,Test_loss:0.176,Lr:2.67E-05
GPU 0 Usage:
Memory Allocated: 442.35 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Epoch:60,Train_acc:98.7%,Train_loss:0.084,Test_acc:92.4%,Test_loss:0.211,Lr:2.46E-05
GPU 0 Usage:
Memory Allocated: 441.16 MB
Memory Cached: 4368.00 MB
Max Memory Allocated: 3604.74 MB
Max Memory Cached: 4368.00 MB
Done best_acc: 0.96
9. 结果可视化
epochs_range = range(epochs)
plt.figure(figsize = (12,3))
plt.subplot(1,2,1)
plt.plot(epochs_range,train_acc,label = 'Training Accuracy')
plt.plot(epochs_range,test_acc,label = 'Test Accuracy')
plt.legend(loc = 'lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1,2,2)
plt.plot(epochs_range,train_loss,label = 'Test Accuracy')
plt.plot(epochs_range,test_loss,label = 'Test Loss')
plt.legend(loc = 'lower right')
plt.title('Training and validation Loss')
plt.show()
10. 模型的保存
# 自定义模型保存
# 状态字典保存
torch.save(model.state_dict(),'./模型参数/J9_InceptionV3_model_state_dict.pth') # 仅保存状态字典
# 定义模型用来加载参数
best_model = InceptionV3(num_classes=len(classNames)).to(device)
best_model.load_state_dict(torch.load('./模型参数/J9_InceptionV3_model_state_dict.pth')) # 加载状态字典到模型
<All keys matched successfully>
11.使用训练好的模型进行预测
# 指定路径图片预测
from PIL import Image
import torchvision.transforms as transforms
classes = list(total_data.class_to_idx) # classes = list(total_data.class_to_idx)
def predict_one_image(image_path,model,transform,classes):
test_img = Image.open(image_path).convert('RGB')
# plt.imshow(test_img) # 展示待预测的图片
test_img = transform(test_img)
img = test_img.to(device).unsqueeze(0)
model.eval()
output = model(img)
print(output) # 观察模型预测结果的输出数据
_,pred = torch.max(output,1)
pred_class = classes[pred]
print(f'预测结果是:{pred_class}')
# 预测训练集中的某张照片
predict_one_image(image_path='./data/weather_recognize/weather_photos/sunrise/sunrise10.jpg',
model = model,
transform = test_transforms,
classes = classes
)
tensor([[-3.4108, -5.2150, -6.3457, 8.8984]], device='cuda:0',
grad_fn=<AddmmBackward0>)
预测结果是:sunrise
classes
['cloudy', 'rain', 'shine', 'sunrise']