J1周：ResNet-50算法实战与解析
- 🍨 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
本周任务
- 根据本文 TensorFlow 代码，编写出相应的 Pytorch 代码
- 了解残差结构
- 是否可以将残差模块融入到C3当中（自由探索）
一、知识储备
深度残差网络ResNet（deep residual network）在2015年由何凯明等提出，因为它简单与实用并存，随后很多研究都是建立在ResNet-50或者ResNet-101基础上完成的。
ResNet主要解决深度卷积网络在深度加深时候的“退化”问题。 在一般的卷积神经网络中，增大网络深度后带来的第一个问题就是梯度消失、爆炸，这个问题在Szegedy提出BN后被顺利解决。BN层能对各层的输出做归一化，这样梯度在反向层层传递后仍能保持大小稳定，不会出现过小或过大的情况。但是作者发现加了BN后，再加大深度仍然不容易收敛，其提到了第二个问题——准确率下降问题：层级大到一定程度时，准确率就会饱和，然后迅速下降。这种下降既不是梯度消失引起的，也不是过拟合造成的，而是由于网络过于复杂，以至于光靠不加约束的放养式的训练很难达到理想的错误率。准确率下降问题不是网络结构本身的问题，而是现有的训练方式不够理想造成的。当前广泛使用的训练方法，无论是SGD，还是RMSProp，或是Adam，都无法在网络深度变大后达到理论上最优的收敛结果。还可以证明只要有理想的训练方式，更深的网络肯定会比较浅的网络效果要好。证明过程也很简单：假设在一种网络A的后面添加几层形成新的网络B，如果增加的层级只是对A的输出做了个恒等映射（identity mapping），即A的输出经过新增的层级变成B的输出后没有发生变化，这样网络A和网络B的错误率就是相等的，也就证明了加深后的网络不会比加深前的网络效果差。
何凯明提出了一种残差结构来实现上述恒等映射：整个模块除了正常的卷积层输出外，还有一个分支把输入直接连到输出上，该分支输出和卷积的输出做算数相加得到最终的输出，用公式表达就是 H ( x ) = F ( x ) + x H(x) = F(x) + xH(x)=F(x)+x，x是输入，F ( x ) F(x)F(x)是卷积分支的输出，H ( x ) H(x)H(x)是整个结构的输出。可以证明如果F ( x ) F(x)F(x)分支中所有参数都是0，H ( x ) H(x)H(x)就是个恒等映射。残差结构人为制造了恒等映射，就能让整个结构朝着恒等映射的方向去收敛，确保最终的错误率不会因为深度的变大而越来越差。如果一个网络通过简单的手工设置参数就能达到想要的结果，那这种结构就很容易通过训练来收敛到该结果，这是一条设计复杂的网络时通用的规则。
上图左边的单元为ResNet两层的残差单元，两层的残差单元包含两个相同输出的通道数的3x3卷积，只是用于较浅的ResNet网络，对较深的网络主要使用三层的残差单元。三层的残差单元又称为bottleneck结构，先用一个1x1卷积进行降维，然后3x3卷积，最后用1x1升维恢复原有的维度。另外，如果有输入输出维度不同的情况，可以对输入做一个线性映射变换维度，再连接后面的层，三层的残差单元对于相同数量的层又减少了参数量，因此可以拓展更深的模型，通过残差单元的组合有经典的ResNet-50，ResNet-101等网络结构。
二、前期工作
1、设置GPU
import torch
import torchvision
if __name__=='__main__':
''' 设置GPU '''
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using {} device\n".format(device))
2、导入数据
root = './jupyternotebook/data'
output = 'output'
data_dir = os.path.join(root, 'bird_photos')
3、查看数据
''' 读取本地数据集并划分训练集与测试集 '''
def localDataset(data_dir):
data_dir = pathlib.Path(data_dir)
# 读取本地数据集
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[-1] for path in data_paths]
# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = torchvision.transforms.Compose([
torchvision.transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
# torchvision.transforms.RandomHorizontalFlip(), # 随机水平翻转
torchvision.transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
torchvision.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],
std=[0.229, 0.224, 0.225]) # 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。
])
total_dataset = torchvision.datasets.ImageFolder(data_dir, transform=train_transforms)
print(total_dataset, '\n')
print(total_dataset.class_to_idx, '\n')
# 划分训练集与测试集
train_size = int(0.8 * len(total_dataset))
test_size = len(total_dataset) - train_size
print('train_size', train_size, 'test_size', test_size, '\n')
train_dataset, test_dataset = torch.utils.data.random_split(total_dataset, [train_size, test_size])
return classeNames, train_dataset, test_dataset
classeNames, train_ds, test_ds = localDataset(data_dir)
num_classes = len(classeNames)
print('num_classes', num_classes)
三、数据预处理
1、加载数据
''' 加载数据，并设置batch_size '''
def loadData(train_ds, test_ds, batch_size=32, root='', show_flag=False):
# 从 train_ds 加载训练集
train_dl = torch.utils.data.DataLoader(train_ds,
batch_size=batch_size,
shuffle=True,
num_workers=1)
# 从 test_ds 加载测试集
test_dl = torch.utils.data.DataLoader(test_ds,
batch_size=batch_size,
shuffle=True,
num_workers=1)
# 取一个批次查看数据格式
# 数据的shape为：[batch_size, channel, height, weight]
# 其中batch_size为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。
for X, y in test_dl:
print('Shape of X [N, C, H, W]: ', X.shape)
print('Shape of y: ', y.shape, y.dtype, '\n')
break
imgs, labels = next(iter(train_dl))
print('Image shape: ', imgs.shape, '\n')
# torch.Size([32, 3, 224, 224]) # 所有数据集中的图像都是224*224的RGB图
displayData(imgs, root, show_flag)
return train_dl, test_dl
batch_size = 8
train_dl, test_dl = loadData(train_ds, test_ds, batch_size, root, True)
2、可视化
''' 数据可视化 '''
def displayData(imgs, root='', flag=False):
# 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure('Data Visualization', figsize=(10, 5))
for i, imgs in enumerate(imgs[:8]):
# 维度顺序调整 [3, 224, 224]->[224, 224, 3]
npimg = imgs.numpy().transpose((1, 2, 0))
# 将整个figure分成2行10列，绘制第i+1个子图。
plt.subplot(2, 4, i+1)
plt.imshow(npimg) # cmap=plt.cm.binary
plt.title(list(classeNames)[labels[i]])
plt.axis('off')
plt.savefig(os.path.join(root, 'DatasetDisplay.png'))
if flag:
plt.show()
else:
plt.close('all')
四、REsNet介绍
1、ResNet解决了什么
残差网络是为了解决神经网络隐藏层过多时，而引起的网络退化问题。退化（degradation）问题是指：当网络隐藏层变多时，网络的准确度达到饱和然后急剧退化，而且这个退化不是由于过拟合引起的。
2、ResNet 50
五、构建ResNet50网络模型
''' Same Padding '''
def autopad(k, p=None): # kernel, padding
# Pad to 'same'
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
''' Identity Block '''
class IdentityBlock(nn.Module):
def __init__(self, in_channel, kernel_size, filters):
super(IdentityBlock, self).__init__()
filters1, filters2, filters3 = filters
self.conv1 = nn.Sequential(
nn.Conv2d(in_channel, filters1, 1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(filters1),
nn.ReLU(True)
)
self.conv2 = nn.Sequential(
nn.Conv2d(filters1, filters2, kernel_size, stride=1, padding=autopad(kernel_size), bias=False),
nn.BatchNorm2d(filters2),
nn.ReLU(True)
)
self.conv3 = nn.Sequential(
nn.Conv2d(filters2, filters3, 1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(filters3)
)
self.relu = nn.ReLU(True)
def forward(self, x):
x1 = self.conv1(x)
x1 = self.conv2(x1)
x1 = self.conv3(x1)
x = x1 + x
self.relu(x)
return x
''' Conv Block '''
class ConvBlock(nn.Module):
def __init__(self, in_channel, kernel_size, filters, stride=2):
super(ConvBlock, self).__init__()
filters1, filters2, filters3 = filters
self.conv1 = nn.Sequential(
nn.Conv2d(in_channel, filters1, 1, stride=stride, padding=0, bias=False),
nn.BatchNorm2d(filters1),
nn.ReLU(True)
)
self.conv2 = nn.Sequential(
nn.Conv2d(filters1, filters2, kernel_size, stride=1, padding=autopad(kernel_size), bias=False),
nn.BatchNorm2d(filters2),
nn.ReLU(True)
)
self.conv3 = nn.Sequential(
nn.Conv2d(filters2, filters3, 1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(filters3)
)
self.conv4 = nn.Sequential(
nn.Conv2d(in_channel, filters3, 1, stride=stride, padding=0, bias=False),
nn.BatchNorm2d(filters3)
)
self.relu = nn.ReLU(True)
def forward(self, x):
x1 = self.conv1(x)
x1 = self.conv2(x1)
x1 = self.conv3(x1)
x2 = self.conv4(x)
x = x1 + x2
self.relu(x)
return x
''' 构建ResNet-50 '''
class ResNet50(nn.Module):
def __init__(self, classes=1000):
super(ResNet50, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3, 64, 7, stride=2, padding=3, bias=False, padding_mode='zeros'),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2, padding=0)
)
self.conv2 = nn.Sequential(
ConvBlock(64, 3, [64, 64, 256], stride=1),
IdentityBlock(256, 3, [64, 64, 256]),
IdentityBlock(256, 3, [64, 64, 256])
)
self.conv3 = nn.Sequential(
ConvBlock(256, 3, [128, 128, 512]),
IdentityBlock(512, 3, [128, 128, 512]),
IdentityBlock(512, 3, [128, 128, 512]),
IdentityBlock(512, 3, [128, 128, 512])
)
self.conv4 = nn.Sequential(
ConvBlock(512, 3, [256, 256, 1024]),
IdentityBlock(1024, 3, [256, 256, 1024]),
IdentityBlock(1024, 3, [256, 256, 1024]),
IdentityBlock(1024, 3, [256, 256, 1024]),
IdentityBlock(1024, 3, [256, 256, 1024]),
IdentityBlock(1024, 3, [256, 256, 1024])
)
self.conv5 = nn.Sequential(
ConvBlock(1024, 3, [512, 512, 2048]),
IdentityBlock(2048, 3, [512, 512, 2048]),
IdentityBlock(2048, 3, [512, 512, 2048])
)
self.pool = nn.AvgPool2d(kernel_size=7, stride=7, padding=0)
self.fc = nn.Linear(2048, n_class)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool(x)
x = torch.flatten(x, start_dim=1)
x = self.fc(x)
return x
model = ResNet50().to(device)
''' 显示网络结构 '''
torchsummary.summary(model, (3, 224, 224))
#torchinfo.summary(model)
print(model)
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,408
BatchNorm2d-2 [-1, 64, 112, 112] 128
ReLU-3 [-1, 64, 112, 112] 0
MaxPool2d-4 [-1, 64, 55, 55] 0
Conv2d-5 [-1, 64, 55, 55] 4,096
BatchNorm2d-6 [-1, 64, 55, 55] 128
ReLU-7 [-1, 64, 55, 55] 0
Conv2d-8 [-1, 64, 55, 55] 36,864
BatchNorm2d-9 [-1, 64, 55, 55] 128
ReLU-10 [-1, 64, 55, 55] 0
Conv2d-11 [-1, 256, 55, 55] 16,384
BatchNorm2d-12 [-1, 256, 55, 55] 512
Conv2d-13 [-1, 256, 55, 55] 16,384
BatchNorm2d-14 [-1, 256, 55, 55] 512
ReLU-15 [-1, 256, 55, 55] 0
ConvBlock-16 [-1, 256, 55, 55] 0
Conv2d-17 [-1, 64, 55, 55] 16,384
BatchNorm2d-18 [-1, 64, 55, 55] 128
ReLU-19 [-1, 64, 55, 55] 0
Conv2d-20 [-1, 64, 55, 55] 36,864
BatchNorm2d-21 [-1, 64, 55, 55] 128
ReLU-22 [-1, 64, 55, 55] 0
Conv2d-23 [-1, 256, 55, 55] 16,384
BatchNorm2d-24 [-1, 256, 55, 55] 512
ReLU-25 [-1, 256, 55, 55] 0
IdentityBlock-26 [-1, 256, 55, 55] 0
Conv2d-27 [-1, 64, 55, 55] 16,384
BatchNorm2d-28 [-1, 64, 55, 55] 128
ReLU-29 [-1, 64, 55, 55] 0
Conv2d-30 [-1, 64, 55, 55] 36,864
BatchNorm2d-31 [-1, 64, 55, 55] 128
ReLU-32 [-1, 64, 55, 55] 0
Conv2d-33 [-1, 256, 55, 55] 16,384
BatchNorm2d-34 [-1, 256, 55, 55] 512
ReLU-35 [-1, 256, 55, 55] 0
IdentityBlock-36 [-1, 256, 55, 55] 0
Conv2d-37 [-1, 128, 28, 28] 32,768
BatchNorm2d-38 [-1, 128, 28, 28] 256
ReLU-39 [-1, 128, 28, 28] 0
Conv2d-40 [-1, 128, 28, 28] 147,456
BatchNorm2d-41 [-1, 128, 28, 28] 256
ReLU-42 [-1, 128, 28, 28] 0
Conv2d-43 [-1, 512, 28, 28] 65,536
BatchNorm2d-44 [-1, 512, 28, 28] 1,024
Conv2d-45 [-1, 512, 28, 28] 131,072
BatchNorm2d-46 [-1, 512, 28, 28] 1,024
ReLU-47 [-1, 512, 28, 28] 0
ConvBlock-48 [-1, 512, 28, 28] 0
Conv2d-49 [-1, 128, 28, 28] 65,536
BatchNorm2d-50 [-1, 128, 28, 28] 256
ReLU-51 [-1, 128, 28, 28] 0
Conv2d-52 [-1, 128, 28, 28] 147,456
BatchNorm2d-53 [-1, 128, 28, 28] 256
ReLU-54 [-1, 128, 28, 28] 0
Conv2d-55 [-1, 512, 28, 28] 65,536
BatchNorm2d-56 [-1, 512, 28, 28] 1,024
ReLU-57 [-1, 512, 28, 28] 0
IdentityBlock-58 [-1, 512, 28, 28] 0
Conv2d-59 [-1, 128, 28, 28] 65,536
BatchNorm2d-60 [-1, 128, 28, 28] 256
ReLU-61 [-1, 128, 28, 28] 0
Conv2d-62 [-1, 128, 28, 28] 147,456
BatchNorm2d-63 [-1, 128, 28, 28] 256
ReLU-64 [-1, 128, 28, 28] 0
Conv2d-65 [-1, 512, 28, 28] 65,536
BatchNorm2d-66 [-1, 512, 28, 28] 1,024
ReLU-67 [-1, 512, 28, 28] 0
IdentityBlock-68 [-1, 512, 28, 28] 0
Conv2d-69 [-1, 128, 28, 28] 65,536
BatchNorm2d-70 [-1, 128, 28, 28] 256
ReLU-71 [-1, 128, 28, 28] 0
Conv2d-72 [-1, 128, 28, 28] 147,456
BatchNorm2d-73 [-1, 128, 28, 28] 256
ReLU-74 [-1, 128, 28, 28] 0
Conv2d-75 [-1, 512, 28, 28] 65,536
BatchNorm2d-76 [-1, 512, 28, 28] 1,024
ReLU-77 [-1, 512, 28, 28] 0
IdentityBlock-78 [-1, 512, 28, 28] 0
Conv2d-79 [-1, 256, 14, 14] 131,072
BatchNorm2d-80 [-1, 256, 14, 14] 512
ReLU-81 [-1, 256, 14, 14] 0
Conv2d-82 [-1, 256, 14, 14] 589,824
BatchNorm2d-83 [-1, 256, 14, 14] 512
ReLU-84 [-1, 256, 14, 14] 0
Conv2d-85 [-1, 1024, 14, 14] 262,144
BatchNorm2d-86 [-1, 1024, 14, 14] 2,048
Conv2d-87 [-1, 1024, 14, 14] 524,288
BatchNorm2d-88 [-1, 1024, 14, 14] 2,048
ReLU-89 [-1, 1024, 14, 14] 0
ConvBlock-90 [-1, 1024, 14, 14] 0
Conv2d-91 [-1, 256, 14, 14] 262,144
BatchNorm2d-92 [-1, 256, 14, 14] 512
ReLU-93 [-1, 256, 14, 14] 0
Conv2d-94 [-1, 256, 14, 14] 589,824
BatchNorm2d-95 [-1, 256, 14, 14] 512
ReLU-96 [-1, 256, 14, 14] 0
Conv2d-97 [-1, 1024, 14, 14] 262,144
BatchNorm2d-98 [-1, 1024, 14, 14] 2,048
ReLU-99 [-1, 1024, 14, 14] 0
IdentityBlock-100 [-1, 1024, 14, 14] 0
Conv2d-101 [-1, 256, 14, 14] 262,144
BatchNorm2d-102 [-1, 256, 14, 14] 512
ReLU-103 [-1, 256, 14, 14] 0
Conv2d-104 [-1, 256, 14, 14] 589,824
BatchNorm2d-105 [-1, 256, 14, 14] 512
ReLU-106 [-1, 256, 14, 14] 0
Conv2d-107 [-1, 1024, 14, 14] 262,144
BatchNorm2d-108 [-1, 1024, 14, 14] 2,048
ReLU-109 [-1, 1024, 14, 14] 0
IdentityBlock-110 [-1, 1024, 14, 14] 0
Conv2d-111 [-1, 256, 14, 14] 262,144
BatchNorm2d-112 [-1, 256, 14, 14] 512
ReLU-113 [-1, 256, 14, 14] 0
Conv2d-114 [-1, 256, 14, 14] 589,824
BatchNorm2d-115 [-1, 256, 14, 14] 512
ReLU-116 [-1, 256, 14, 14] 0
Conv2d-117 [-1, 1024, 14, 14] 262,144
BatchNorm2d-118 [-1, 1024, 14, 14] 2,048
ReLU-119 [-1, 1024, 14, 14] 0
IdentityBlock-120 [-1, 1024, 14, 14] 0
Conv2d-121 [-1, 256, 14, 14] 262,144
BatchNorm2d-122 [-1, 256, 14, 14] 512
ReLU-123 [-1, 256, 14, 14] 0
Conv2d-124 [-1, 256, 14, 14] 589,824
BatchNorm2d-125 [-1, 256, 14, 14] 512
ReLU-126 [-1, 256, 14, 14] 0
Conv2d-127 [-1, 1024, 14, 14] 262,144
BatchNorm2d-128 [-1, 1024, 14, 14] 2,048
ReLU-129 [-1, 1024, 14, 14] 0
IdentityBlock-130 [-1, 1024, 14, 14] 0
Conv2d-131 [-1, 256, 14, 14] 262,144
BatchNorm2d-132 [-1, 256, 14, 14] 512
ReLU-133 [-1, 256, 14, 14] 0
Conv2d-134 [-1, 256, 14, 14] 589,824
BatchNorm2d-135 [-1, 256, 14, 14] 512
ReLU-136 [-1, 256, 14, 14] 0
Conv2d-137 [-1, 1024, 14, 14] 262,144
BatchNorm2d-138 [-1, 1024, 14, 14] 2,048
ReLU-139 [-1, 1024, 14, 14] 0
IdentityBlock-140 [-1, 1024, 14, 14] 0
Conv2d-141 [-1, 512, 7, 7] 524,288
BatchNorm2d-142 [-1, 512, 7, 7] 1,024
ReLU-143 [-1, 512, 7, 7] 0
Conv2d-144 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-145 [-1, 512, 7, 7] 1,024
ReLU-146 [-1, 512, 7, 7] 0
Conv2d-147 [-1, 2048, 7, 7] 1,048,576
BatchNorm2d-148 [-1, 2048, 7, 7] 4,096
Conv2d-149 [-1, 2048, 7, 7] 2,097,152
BatchNorm2d-150 [-1, 2048, 7, 7] 4,096
ReLU-151 [-1, 2048, 7, 7] 0
ConvBlock-152 [-1, 2048, 7, 7] 0
Conv2d-153 [-1, 512, 7, 7] 1,048,576
BatchNorm2d-154 [-1, 512, 7, 7] 1,024
ReLU-155 [-1, 512, 7, 7] 0
Conv2d-156 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-157 [-1, 512, 7, 7] 1,024
ReLU-158 [-1, 512, 7, 7] 0
Conv2d-159 [-1, 2048, 7, 7] 1,048,576
BatchNorm2d-160 [-1, 2048, 7, 7] 4,096
ReLU-161 [-1, 2048, 7, 7] 0
IdentityBlock-162 [-1, 2048, 7, 7] 0
Conv2d-163 [-1, 512, 7, 7] 1,048,576
BatchNorm2d-164 [-1, 512, 7, 7] 1,024
ReLU-165 [-1, 512, 7, 7] 0
Conv2d-166 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-167 [-1, 512, 7, 7] 1,024
ReLU-168 [-1, 512, 7, 7] 0
Conv2d-169 [-1, 2048, 7, 7] 1,048,576
BatchNorm2d-170 [-1, 2048, 7, 7] 4,096
ReLU-171 [-1, 2048, 7, 7] 0
IdentityBlock-172 [-1, 2048, 7, 7] 0
AvgPool2d-173 [-1, 2048, 1, 1] 0
Linear-174 [-1, 4] 8,196
================================================================
Total params: 23,516,228
Trainable params: 23,516,228
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 270.43
Params size (MB): 89.71
Estimated Total Size (MB): 360.71
----------------------------------------------------------------
ResNet50(
(conv1): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU()
(3): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(conv2): Sequential(
(0): ConvBlock(
(conv1): Sequential(
(0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv4): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(2): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(conv3): Sequential(
(0): ConvBlock(
(conv1): Sequential(
(0): Conv2d(256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv4): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(2): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(3): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(conv4): Sequential(
(0): ConvBlock(
(conv1): Sequential(
(0): Conv2d(512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv4): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(2): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(3): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(4): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(5): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(conv5): Sequential(
(0): ConvBlock(
(conv1): Sequential(
(0): Conv2d(1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv4): Sequential(
(0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(2): IdentityBlock(
(conv1): Sequential(
(0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv3): Sequential(
(0): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
(pool): AvgPool2d(kernel_size=7, stride=7, padding=0)
(fc): Linear(in_features=2048, out_features=4, bias=True)
)
六、设置超参数
''' 设置超参数 '''
start_epoch = 0
epochs = 10
learn_rate = 1e-7 # 初始学习率
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
optimizer = torch.optim.Adam(model.parameters(),lr=learn_rate)
train_loss = []
train_acc = []
test_loss = []
test_acc = []
epoch_best_acc = 0
七、训练模型
''' 训练循环 '''
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小
num_batches = len(dataloader) # 批次数目
train_loss, train_acc = 0, 0 # 初始化训练损失和正确率
for X, y in dataloader: # 获取图片及其标签
X, y = X.to(device), y.to(device)
# 计算预测误差
pred = model(X) # 网络输出
loss = loss_fn(pred, y) # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
# 反向传播
optimizer.zero_grad() # grad属性归零
loss.backward() # 反向传播
optimizer.step() # 每一步自动更新
# 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
''' 测试函数 '''
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目
test_loss, test_acc = 0, 0
# 当不进行训练时，停止梯度更新，节省计算内存消耗
with torch.no_grad():
for imgs, target in dataloader:
imgs, target = imgs.to(device), target.to(device)
# 计算loss
target_pred = model(imgs)
loss = loss_fn(target_pred, target)
test_loss += loss.item()
test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
''' 加载之前保存的模型 '''
if not os.path.exists(output) or not os.path.isdir(output):
os.makedirs(output)
if start_epoch > 0:
resumeFile = os.path.join(output, 'epoch'+str(start_epoch)+'.pkl')
if not os.path.exists(resumeFile) or not os.path.isfile(resumeFile):
start_epoch = 0
else:
model.load_state_dict(torch.load(resumeFile)) # 加载模型参数
''' 开始训练模型 '''
print('\nStart training...')
best_model = None
for epoch in range(start_epoch, epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前的学习率
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(time.strftime('[%Y-%m-%d %H:%M:%S]'), template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr))
# 保存最佳模型
if epoch_test_acc>epoch_best_acc:
''' 保存最优模型参数 '''
epoch_best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
print(('acc = {:.1f}%, saving model to best.pkl').format(epoch_best_acc*100))
saveFile = os.path.join(output, 'best.pkl')
torch.save(best_model.state_dict(), saveFile)
if epoch_test_acc==1 and epoch_train_acc==1:
saveFile = os.path.join(output, 'epoch'+str(epoch+1)+'.pkl')
torch.save(model.state_dict(), saveFile)
print('Done\n')
''' 保存模型参数 '''
saveFile = os.path.join(output, 'epoch'+str(epochs)+'.pkl')
torch.save(model.state_dict(), saveFile)
Start training...
[2023-02-09 14:40:46] Epoch: 1, Train_acc:20.6%, Train_loss:1.645, Test_acc:16.8%, Test_loss:1.576, Lr:1.00E-07
acc = 16.8%, saving model to best.pkl
[2023-02-09 14:41:35] Epoch: 2, Train_acc:23.7%, Train_loss:1.624, Test_acc:20.4%, Test_loss:1.721, Lr:1.00E-07
acc = 20.4%, saving model to best.pkl
[2023-02-09 14:41:46] Epoch: 3, Train_acc:23.2%, Train_loss:1.623, Test_acc:15.9%, Test_loss:1.610, Lr:1.00E-07
[2023-02-09 14:41:57] Epoch: 4, Train_acc:22.8%, Train_loss:1.617, Test_acc:18.6%, Test_loss:1.676, Lr:1.00E-07
[2023-02-09 14:42:08] Epoch: 5, Train_acc:22.1%, Train_loss:1.607, Test_acc:20.4%, Test_loss:1.661, Lr:1.00E-07
[2023-02-09 14:42:19] Epoch: 6, Train_acc:23.2%, Train_loss:1.606, Test_acc:15.9%, Test_loss:1.599, Lr:1.00E-07
[2023-02-09 14:42:30] Epoch: 7, Train_acc:25.2%, Train_loss:1.592, Test_acc:19.5%, Test_loss:1.655, Lr:1.00E-07
[2023-02-09 14:42:40] Epoch: 8, Train_acc:22.6%, Train_loss:1.595, Test_acc:15.0%, Test_loss:1.626, Lr:1.00E-07
[2023-02-09 14:42:50] Epoch: 9, Train_acc:23.9%, Train_loss:1.588, Test_acc:18.6%, Test_loss:1.614, Lr:1.00E-07
[2023-02-09 14:43:01] Epoch:10, Train_acc:24.6%, Train_loss:1.577, Test_acc:22.1%, Test_loss:1.558, Lr:1.00E-07
acc = 22.1%, saving model to best.pkl
Done
八、模型评估
''' 结果可视化 '''
def displayResult(train_acc, test_acc, train_loss, test_loss, start_epoch, epochs, output=''):
# 隐藏警告
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
epochs_range = range(start_epoch, epochs)
plt.figure('Result Visualization', 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='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.savefig(os.path.join(output, 'AccuracyLoss.png'))
plt.show()
''' 绘制准确率&损失率曲线图 '''
displayResult(train_acc, test_acc, train_loss, test_loss, start_epoch, epochs, output)
''' 模型评估 '''
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
print("EVAL {:.5f}, {:.5f}".format(epoch_test_acc, epoch_test_loss))
九、预测
''' 预测函数 '''
def predict(model, img_path):
img = Image.open(img_path)
train_transforms = torchvision.transforms.Compose([
torchvision.transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
torchvision.transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
torchvision.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],
std=[0.229, 0.224, 0.225]) # 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。
])
img = train_transforms(img)
img = torch.reshape(img, (1, 3, 224, 224))
output = model(img.cuda())
#print(output.argmax(1))
_, indices = torch.max(output, 1)
percentage = torch.nn.functional.softmax(output, dim=1)[0] * 100
perc = percentage[int(indices)].item()
result = classeNames[indices]
print('predicted:', result, perc)
if __name__=='__main__':
classeNames = ['Bananaquit', 'Black Throated Bushtiti', 'Black skimmer', 'Cockatoo']
num_classes = len(classeNames)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using {} device\n".format(device))
model = ResNet50(num_classes).to(device)
model.load_state_dict(torch.load(os.path.join('output', 'best.pkl')))
model.eval()
img_path = './data/bird_photos/Bananaquit/009.jpg'
#img_path = './data/bird_photos/Cockatoo/016.jpg'
predict(model, img_path)
