深度学习笔记35_Inception v1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
一、我的环境：
1.语言环境：Python 3.8
2.编译器：Pycharm
3.深度学习环境：
- torch==1.12.1+cu113
- torchvision==0.13.1+cu113
二、GPU设置：
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)三、导入数据：
import os,PIL,random,pathlib
data_dir = './data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
print(classeNames)运行结果：
['Monkeypox', 'Others']total_datadir = './data/'
# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为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],
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_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
print(total_data)运行结果：
Dataset ImageFolder
Number of datapoints: 2142
Root location: ./data/
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=None)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)四、数据可视化：
# 指定图像文件夹路径
image_folder = './data/Others/'
# 获取文件夹中的所有图像文件
image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
# 创建Matplotlib图像
fig, axes = plt.subplots(2, 4, figsize=(16, 6))
# 使用列表推导式加载和显示图像
for ax, img_file in zip(axes.flat, image_files):
img_path = os.path.join(image_folder, img_file)
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
# 显示图像
plt.tight_layout()
plt.show()运行结果：
五、划分数据集
train_size = int(0.8 * len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
print(train_size,test_size)batch_size = 32
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)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运行结果：
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64六、构建模型
class inception_block(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(inception_block, self).__init__()
# 1x1 conv branch
self.branch1 = nn.Sequential(
nn.Conv2d(in_channels, ch1x1, kernel_size=1),
nn.BatchNorm2d(ch1x1),
nn.ReLU(inplace=True)
)
# 1x1 conv -> 3x3 conv branch
self.branch2 = nn.Sequential(
nn.Conv2d(in_channels, ch3x3red, kernel_size=1),
nn.BatchNorm2d(ch3x3red),
nn.ReLU(inplace=True),
nn.Conv2d(ch3x3red, ch3x3, kernel_size=3, padding=1),
nn.BatchNorm2d(ch3x3),
nn.ReLU(inplace=True)
)
# 1x1 conv -> 5x5 conv branch
self.branch3 = nn.Sequential(
nn.Conv2d(in_channels, ch5x5red, kernel_size=1),
nn.BatchNorm2d(ch5x5red),
nn.ReLU(inplace=True),
nn.Conv2d(ch5x5red, ch5x5, kernel_size=5, padding=2),
nn.BatchNorm2d(ch5x5),
nn.ReLU(inplace=True)
)
# 3x3 max pooling -> 1x1 conv branch
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
nn.Conv2d(in_channels, pool_proj, kernel_size=1),
nn.BatchNorm2d(pool_proj),
nn.ReLU(inplace=True)
)
def forward(self, x):
# compute forward pass through all branches
# and concatenate the outout feature maps
branch1_output = self.branch1(x)
branch2_output = self.branch2(x)
branch3_output = self.branch3(x)
branch4_output = self.branch4(x)
outputs = [branch1_output, branch2_output, branch3_output, branch4_output]
return torch.cat(outputs, 1)
class InceptionV1(nn.Module):
def __init__(self, num_classes=4):
super(InceptionV1, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.conv2 = nn.Conv2d(64, 64, kernel_size=1, stride=1, padding=0)
self.conv3 = nn.Conv2d(64, 192, kernel_size=3, stride=1, padding=1)
self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32)
self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64)
self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64)
self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64)
self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64)
self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128)
self.inception5b = nn.Sequential(
inception_block(832, 384, 192, 384, 48, 128, 128),
nn.AvgPool2d(kernel_size=7, stride=1, padding=0),
nn.Dropout(0.4)
)
# 全连接网络层，用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=1024, out_features=1024),
nn.ReLU(),
nn.Linear(in_features=1024, out_features=num_classes),
nn.Softmax(dim=1)
)
def forward(self, x):
x = self.conv1(x)
x = F.relu(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = F.relu(x)
x = self.conv3(x)
x = F.relu(x)
x = self.maxpool2(x)
x = self.inception3a(x)
x = self.inception3b(x)
x = self.maxpool3(x)
x = self.inception4a(x)
x = self.inception4b(x)
x = self.inception4c(x)
x = self.inception4d(x)
x = self.inception4e(x)
x = self.maxpool4(x)
x = self.inception5a(x)
x = self.inception5b(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
# 调用并将模型转移到GPU中
model = InceptionV1().to(device)
加载并打印模型
torchsummary.summary(model, (3, 224, 224))
print(model)运行结果：
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,472
MaxPool2d-2 [-1, 64, 56, 56] 0
Conv2d-3 [-1, 64, 56, 56] 4,160
Conv2d-4 [-1, 192, 56, 56] 110,784
MaxPool2d-5 [-1, 192, 28, 28] 0
Conv2d-6 [-1, 64, 28, 28] 12,352
BatchNorm2d-7 [-1, 64, 28, 28] 128
ReLU-8 [-1, 64, 28, 28] 0
Conv2d-9 [-1, 96, 28, 28] 18,528
BatchNorm2d-10 [-1, 96, 28, 28] 192
ReLU-11 [-1, 96, 28, 28] 0
Conv2d-12 [-1, 128, 28, 28] 110,720
BatchNorm2d-13 [-1, 128, 28, 28] 256
ReLU-14 [-1, 128, 28, 28] 0
Conv2d-15 [-1, 16, 28, 28] 3,088
BatchNorm2d-16 [-1, 16, 28, 28] 32
ReLU-17 [-1, 16, 28, 28] 0
Conv2d-18 [-1, 32, 28, 28] 12,832
BatchNorm2d-19 [-1, 32, 28, 28] 64
ReLU-20 [-1, 32, 28, 28] 0
MaxPool2d-21 [-1, 192, 28, 28] 0
Conv2d-22 [-1, 32, 28, 28] 6,176
BatchNorm2d-23 [-1, 32, 28, 28] 64
ReLU-24 [-1, 32, 28, 28] 0
inception_block-25 [-1, 256, 28, 28] 0
Conv2d-26 [-1, 128, 28, 28] 32,896
BatchNorm2d-27 [-1, 128, 28, 28] 256
ReLU-28 [-1, 128, 28, 28] 0
Conv2d-29 [-1, 128, 28, 28] 32,896
BatchNorm2d-30 [-1, 128, 28, 28] 256
ReLU-31 [-1, 128, 28, 28] 0
Conv2d-32 [-1, 192, 28, 28] 221,376
BatchNorm2d-33 [-1, 192, 28, 28] 384
ReLU-34 [-1, 192, 28, 28] 0
Conv2d-35 [-1, 32, 28, 28] 8,224
BatchNorm2d-36 [-1, 32, 28, 28] 64
ReLU-37 [-1, 32, 28, 28] 0
Conv2d-38 [-1, 96, 28, 28] 76,896
BatchNorm2d-39 [-1, 96, 28, 28] 192
ReLU-40 [-1, 96, 28, 28] 0
MaxPool2d-41 [-1, 256, 28, 28] 0
Conv2d-42 [-1, 64, 28, 28] 16,448
BatchNorm2d-43 [-1, 64, 28, 28] 128
ReLU-44 [-1, 64, 28, 28] 0
inception_block-45 [-1, 480, 28, 28] 0
MaxPool2d-46 [-1, 480, 14, 14] 0
Conv2d-47 [-1, 192, 14, 14] 92,352
BatchNorm2d-48 [-1, 192, 14, 14] 384
ReLU-49 [-1, 192, 14, 14] 0
Conv2d-50 [-1, 96, 14, 14] 46,176
BatchNorm2d-51 [-1, 96, 14, 14] 192
ReLU-52 [-1, 96, 14, 14] 0
Conv2d-53 [-1, 208, 14, 14] 179,920
BatchNorm2d-54 [-1, 208, 14, 14] 416
ReLU-55 [-1, 208, 14, 14] 0
Conv2d-56 [-1, 16, 14, 14] 7,696
BatchNorm2d-57 [-1, 16, 14, 14] 32
ReLU-58 [-1, 16, 14, 14] 0
Conv2d-59 [-1, 48, 14, 14] 19,248
BatchNorm2d-60 [-1, 48, 14, 14] 96
ReLU-61 [-1, 48, 14, 14] 0
MaxPool2d-62 [-1, 480, 14, 14] 0
Conv2d-63 [-1, 64, 14, 14] 30,784
BatchNorm2d-64 [-1, 64, 14, 14] 128
ReLU-65 [-1, 64, 14, 14] 0
inception_block-66 [-1, 512, 14, 14] 0
Conv2d-67 [-1, 160, 14, 14] 82,080
BatchNorm2d-68 [-1, 160, 14, 14] 320
ReLU-69 [-1, 160, 14, 14] 0
Conv2d-70 [-1, 112, 14, 14] 57,456
BatchNorm2d-71 [-1, 112, 14, 14] 224
ReLU-72 [-1, 112, 14, 14] 0
Conv2d-73 [-1, 224, 14, 14] 226,016
BatchNorm2d-74 [-1, 224, 14, 14] 448
ReLU-75 [-1, 224, 14, 14] 0
Conv2d-76 [-1, 24, 14, 14] 12,312
BatchNorm2d-77 [-1, 24, 14, 14] 48
ReLU-78 [-1, 24, 14, 14] 0
Conv2d-79 [-1, 64, 14, 14] 38,464
BatchNorm2d-80 [-1, 64, 14, 14] 128
ReLU-81 [-1, 64, 14, 14] 0
MaxPool2d-82 [-1, 512, 14, 14] 0
Conv2d-83 [-1, 64, 14, 14] 32,832
BatchNorm2d-84 [-1, 64, 14, 14] 128
ReLU-85 [-1, 64, 14, 14] 0
inception_block-86 [-1, 512, 14, 14] 0
Conv2d-87 [-1, 128, 14, 14] 65,664
BatchNorm2d-88 [-1, 128, 14, 14] 256
ReLU-89 [-1, 128, 14, 14] 0
Conv2d-90 [-1, 128, 14, 14] 65,664
BatchNorm2d-91 [-1, 128, 14, 14] 256
ReLU-92 [-1, 128, 14, 14] 0
Conv2d-93 [-1, 256, 14, 14] 295,168
BatchNorm2d-94 [-1, 256, 14, 14] 512
ReLU-95 [-1, 256, 14, 14] 0
Conv2d-96 [-1, 24, 14, 14] 12,312
BatchNorm2d-97 [-1, 24, 14, 14] 48
ReLU-98 [-1, 24, 14, 14] 0
Conv2d-99 [-1, 64, 14, 14] 38,464
BatchNorm2d-100 [-1, 64, 14, 14] 128
ReLU-101 [-1, 64, 14, 14] 0
MaxPool2d-102 [-1, 512, 14, 14] 0
Conv2d-103 [-1, 64, 14, 14] 32,832
BatchNorm2d-104 [-1, 64, 14, 14] 128
ReLU-105 [-1, 64, 14, 14] 0
inception_block-106 [-1, 512, 14, 14] 0
Conv2d-107 [-1, 112, 14, 14] 57,456
BatchNorm2d-108 [-1, 112, 14, 14] 224
ReLU-109 [-1, 112, 14, 14] 0
Conv2d-110 [-1, 144, 14, 14] 73,872
BatchNorm2d-111 [-1, 144, 14, 14] 288
ReLU-112 [-1, 144, 14, 14] 0
Conv2d-113 [-1, 288, 14, 14] 373,536
BatchNorm2d-114 [-1, 288, 14, 14] 576
ReLU-115 [-1, 288, 14, 14] 0
Conv2d-116 [-1, 32, 14, 14] 16,416
BatchNorm2d-117 [-1, 32, 14, 14] 64
ReLU-118 [-1, 32, 14, 14] 0
Conv2d-119 [-1, 64, 14, 14] 51,264
BatchNorm2d-120 [-1, 64, 14, 14] 128
ReLU-121 [-1, 64, 14, 14] 0
MaxPool2d-122 [-1, 512, 14, 14] 0
Conv2d-123 [-1, 64, 14, 14] 32,832
BatchNorm2d-124 [-1, 64, 14, 14] 128
ReLU-125 [-1, 64, 14, 14] 0
inception_block-126 [-1, 528, 14, 14] 0
Conv2d-127 [-1, 256, 14, 14] 135,424
BatchNorm2d-128 [-1, 256, 14, 14] 512
ReLU-129 [-1, 256, 14, 14] 0
Conv2d-130 [-1, 160, 14, 14] 84,640
BatchNorm2d-131 [-1, 160, 14, 14] 320
ReLU-132 [-1, 160, 14, 14] 0
Conv2d-133 [-1, 320, 14, 14] 461,120
BatchNorm2d-134 [-1, 320, 14, 14] 640
ReLU-135 [-1, 320, 14, 14] 0
Conv2d-136 [-1, 32, 14, 14] 16,928
BatchNorm2d-137 [-1, 32, 14, 14] 64
ReLU-138 [-1, 32, 14, 14] 0
Conv2d-139 [-1, 128, 14, 14] 102,528
BatchNorm2d-140 [-1, 128, 14, 14] 256
ReLU-141 [-1, 128, 14, 14] 0
MaxPool2d-142 [-1, 528, 14, 14] 0
Conv2d-143 [-1, 128, 14, 14] 67,712
BatchNorm2d-144 [-1, 128, 14, 14] 256
ReLU-145 [-1, 128, 14, 14] 0
inception_block-146 [-1, 832, 14, 14] 0
MaxPool2d-147 [-1, 832, 7, 7] 0
Conv2d-148 [-1, 256, 7, 7] 213,248
BatchNorm2d-149 [-1, 256, 7, 7] 512
ReLU-150 [-1, 256, 7, 7] 0
Conv2d-151 [-1, 160, 7, 7] 133,280
BatchNorm2d-152 [-1, 160, 7, 7] 320
ReLU-153 [-1, 160, 7, 7] 0
Conv2d-154 [-1, 320, 7, 7] 461,120
BatchNorm2d-155 [-1, 320, 7, 7] 640
ReLU-156 [-1, 320, 7, 7] 0
Conv2d-157 [-1, 32, 7, 7] 26,656
BatchNorm2d-158 [-1, 32, 7, 7] 64
ReLU-159 [-1, 32, 7, 7] 0
Conv2d-160 [-1, 128, 7, 7] 102,528
BatchNorm2d-161 [-1, 128, 7, 7] 256
ReLU-162 [-1, 128, 7, 7] 0
MaxPool2d-163 [-1, 832, 7, 7] 0
Conv2d-164 [-1, 128, 7, 7] 106,624
BatchNorm2d-165 [-1, 128, 7, 7] 256
ReLU-166 [-1, 128, 7, 7] 0
inception_block-167 [-1, 832, 7, 7] 0
Conv2d-168 [-1, 384, 7, 7] 319,872
BatchNorm2d-169 [-1, 384, 7, 7] 768
ReLU-170 [-1, 384, 7, 7] 0
Conv2d-171 [-1, 192, 7, 7] 159,936
BatchNorm2d-172 [-1, 192, 7, 7] 384
ReLU-173 [-1, 192, 7, 7] 0
Conv2d-174 [-1, 384, 7, 7] 663,936
BatchNorm2d-175 [-1, 384, 7, 7] 768
ReLU-176 [-1, 384, 7, 7] 0
Conv2d-177 [-1, 48, 7, 7] 39,984
BatchNorm2d-178 [-1, 48, 7, 7] 96
ReLU-179 [-1, 48, 7, 7] 0
Conv2d-180 [-1, 128, 7, 7] 153,728
BatchNorm2d-181 [-1, 128, 7, 7] 256
ReLU-182 [-1, 128, 7, 7] 0
MaxPool2d-183 [-1, 832, 7, 7] 0
Conv2d-184 [-1, 128, 7, 7] 106,624
BatchNorm2d-185 [-1, 128, 7, 7] 256
ReLU-186 [-1, 128, 7, 7] 0
inception_block-187 [-1, 1024, 7, 7] 0
AvgPool2d-188 [-1, 1024, 1, 1] 0
Dropout-189 [-1, 1024, 1, 1] 0
Linear-190 [-1, 1024] 1,049,600
ReLU-191 [-1, 1024] 0
Linear-192 [-1, 4] 4,100
Softmax-193 [-1, 4] 0
================================================================
Total params: 7,041,172
Trainable params: 7,041,172
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 69.61
Params size (MB): 26.86
Estimated Total Size (MB): 97.05
----------------------------------------------------------------
InceptionV1(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
(maxpool1): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(conv2): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(conv3): Conv2d(64, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(maxpool2): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(inception3a): inception_block(
(branch1): Sequential(
(0): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(96, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(192, 16, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(inception3b): inception_block(
(branch1): Sequential(
(0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(32, 96, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(maxpool3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(inception4a): inception_block(
(branch1): Sequential(
(0): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(480, 96, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(96, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(480, 16, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(16, 48, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(480, 64, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(inception4b): inception_block(
(branch1): Sequential(
(0): Conv2d(512, 160, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(112, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(inception4c): inception_block(
(branch1): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(inception4d): inception_block(
(branch1): Sequential(
(0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(512, 144, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(144, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(inception4e): inception_block(
(branch1): Sequential(
(0): Conv2d(528, 256, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(528, 160, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(528, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(528, 128, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(maxpool4): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(inception5a): inception_block(
(branch1): Sequential(
(0): Conv2d(832, 256, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(832, 160, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(832, 32, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(inception5b): Sequential(
(0): inception_block(
(branch1): Sequential(
(0): Conv2d(832, 384, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(branch2): Sequential(
(0): Conv2d(832, 192, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch3): Sequential(
(0): Conv2d(832, 48, kernel_size=(1, 1), stride=(1, 1))
(1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): ReLU(inplace=True)
)
(branch4): Sequential(
(0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))
(2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): ReLU(inplace=True)
)
)
(1): AvgPool2d(kernel_size=7, stride=1, padding=0)
(2): Dropout(p=0.4, inplace=False)
)
(classifier): Sequential(
(0): Linear(in_features=1024, out_features=1024, bias=True)
(1): ReLU()
(2): Linear(in_features=1024, out_features=4, bias=True)
(3): Softmax(dim=1)
)
)
七、训练函数
# 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, (size/batch_size，向上取整)
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pred和真实值y之间的差距，y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八、测试函数
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset) # 训练集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整)
test_loss, test_acc = 0, 0 # 初始化测试损失和正确率
# 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: # 获取图片及其标签
with torch.no_grad():
imgs, target = imgs.to(device), target.to(device)
# 计算误差
tartget_pred = model(imgs) # 网络输出
loss = loss_fn(tartget_pred, target) # 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
# 记录acc与loss
test_loss += loss.item()
test_acc += (tartget_pred.argmax(1) == target).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss九、模型训练
if __name__ == "__main__":
main()def main():
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 40
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 设置一个最佳准确率，作为最佳模型的判别指标
if hasattr(torch.cuda, 'empty_cache'):
torch.cuda.empty_cache()
for epoch in range(epochs):
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接口时使用）
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(
template.format(epoch + 1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc * 100, epoch_test_loss, lr))
PATH = './best_model.pth'
torch.save(model.state_dict(), PATH)
print('Done')运行结果：
Epoch: 1. Train_acc: 59.4%, Train_loss: 1.142, Test_acc:61.8%, Test_loss:1.118, Lr: 1.00E-04
Epoch: 2. Train_acc: 61.3%, Train_loss: 1.116, Test_acc:61.1%, Test_loss:1.131, Lr: 1.00E-04
Epoch: 3. Train_acc: 63.6%, Train_loss: 1.096, Test_acc:61.3%, Test_loss:1.115, Lr: 1.00E-04
Epoch: 4. Train_acc: 68.0%, Train_loss: 1.057, Test_acc:64.1%, Test_loss:1.099, Lr: 1.00E-04
Epoch: 5. Train_acc: 66.8%, Train_loss: 1.071, Test_acc:64.3%, Test_loss:1.095, Lr: 1.00E-04
Epoch: 6. Train_acc: 63.7%, Train_loss: 1.100, Test_acc:70.2%, Test_loss:1.042, Lr: 1.00E-04
Epoch: 7. Train_acc: 67.9%, Train_loss: 1.059, Test_acc:70.6%, Test_loss:1.037, Lr: 1.00E-04
Epoch: 8. Train_acc: 64.6%, Train_loss: 1.093, Test_acc:71.6%, Test_loss:1.027, Lr: 1.00E-04
Epoch: 9. Train_acc: 70.2%, Train_loss: 1.033, Test_acc:66.7%, Test_loss:1.070, Lr: 1.00E-04
Epoch: 10. Train_acc: 69.2%, Train_loss: 1.045, Test_acc:70.4%, Test_loss:1.032, Lr: 1.00E-04
Epoch: 11. Train_acc: 69.4%, Train_loss: 1.048, Test_acc:71.3%, Test_loss:1.036, Lr: 1.00E-04
Epoch: 12. Train_acc: 69.9%, Train_loss: 1.045, Test_acc:68.5%, Test_loss:1.054, Lr: 1.00E-04
Epoch: 13. Train_acc: 68.8%, Train_loss: 1.053, Test_acc:73.7%, Test_loss:1.012, Lr: 1.00E-04
Epoch: 14. Train_acc: 72.5%, Train_loss: 1.016, Test_acc:76.7%, Test_loss:0.978, Lr: 1.00E-04
Epoch: 15. Train_acc: 72.3%, Train_loss: 1.016, Test_acc:71.3%, Test_loss:1.035, Lr: 1.00E-04
Epoch: 16. Train_acc: 73.5%, Train_loss: 1.007, Test_acc:74.8%, Test_loss:1.003, Lr: 1.00E-04
Epoch: 17. Train_acc: 74.7%, Train_loss: 0.991, Test_acc:80.7%, Test_loss:0.941, Lr: 1.00E-04
Epoch: 18. Train_acc: 74.3%, Train_loss: 0.998, Test_acc:76.2%, Test_loss:0.974, Lr: 1.00E-04
Epoch: 19. Train_acc: 75.5%, Train_loss: 0.987, Test_acc:77.4%, Test_loss:0.972, Lr: 1.00E-04
Epoch: 20. Train_acc: 73.0%, Train_loss: 1.010, Test_acc:76.2%, Test_loss:0.988, Lr: 1.00E-04
Epoch: 21. Train_acc: 74.8%, Train_loss: 0.990, Test_acc:78.3%, Test_loss:0.957, Lr: 1.00E-04
Epoch: 22. Train_acc: 75.5%, Train_loss: 0.985, Test_acc:79.5%, Test_loss:0.950, Lr: 1.00E-04
Epoch: 23. Train_acc: 80.0%, Train_loss: 0.943, Test_acc:80.2%, Test_loss:0.935, Lr: 1.00E-04
Epoch: 24. Train_acc: 78.9%, Train_loss: 0.952, Test_acc:80.9%, Test_loss:0.936, Lr: 1.00E-04
Epoch: 25. Train_acc: 73.6%, Train_loss: 1.005, Test_acc:69.9%, Test_loss:1.045, Lr: 1.00E-04
Epoch: 26. Train_acc: 78.6%, Train_loss: 0.959, Test_acc:81.4%, Test_loss:0.931, Lr: 1.00E-04
Epoch: 27. Train_acc: 77.2%, Train_loss: 0.970, Test_acc:69.5%, Test_loss:1.047, Lr: 1.00E-04
Epoch: 28. Train_acc: 77.1%, Train_loss: 0.973, Test_acc:80.7%, Test_loss:0.939, Lr: 1.00E-04
Epoch: 29. Train_acc: 79.2%, Train_loss: 0.949, Test_acc:76.7%, Test_loss:0.972, Lr: 1.00E-04
Epoch: 30. Train_acc: 78.3%, Train_loss: 0.954, Test_acc:83.0%, Test_loss:0.915, Lr: 1.00E-04
Epoch: 31. Train_acc: 81.3%, Train_loss: 0.925, Test_acc:80.4%, Test_loss:0.938, Lr: 1.00E-04
Epoch: 32. Train_acc: 81.0%, Train_loss: 0.929, Test_acc:84.4%, Test_loss:0.898, Lr: 1.00E-04
Epoch: 33. Train_acc: 82.0%, Train_loss: 0.921, Test_acc:85.8%, Test_loss:0.884, Lr: 1.00E-04
Epoch: 34. Train_acc: 83.8%, Train_loss: 0.903, Test_acc:84.8%, Test_loss:0.898, Lr: 1.00E-04
Epoch: 35. Train_acc: 84.8%, Train_loss: 0.895, Test_acc:87.6%, Test_loss:0.866, Lr: 1.00E-04
Epoch: 36. Train_acc: 79.7%, Train_loss: 0.940, Test_acc:82.5%, Test_loss:0.921, Lr: 1.00E-04
Epoch: 37. Train_acc: 85.3%, Train_loss: 0.894, Test_acc:81.6%, Test_loss:0.925, Lr: 1.00E-04
Epoch: 38. Train_acc: 80.0%, Train_loss: 0.941, Test_acc:75.5%, Test_loss:0.985, Lr: 1.00E-04
Epoch: 39. Train_acc: 81.4%, Train_loss: 0.926, Test_acc:81.4%, Test_loss:0.935, Lr: 1.00E-04
Epoch: 40. Train_acc: 83.5%, Train_loss: 0.909, Test_acc:85.5%, Test_loss:0.886, Lr: 1.00E-04
Done十、模型评估
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(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='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()运行结果：
十一、总结
本次Inception v1算法实战与解析项目总结如下：
Inception Module是Inception V1的核心组成单元，提出了卷积层的并行结构，实现了在同一层就可以提取不同的特征，如下图（a)所示。
按照这样的结构来增加网络的深度，虽然可以提升性能，但是还面临计算量大（参数多）的问题。为改善这种现象，Inception Module借鉴Network-in-Network的思想，使用1x1的卷积核实现降维操作（也间接增加了网络的深度），以此来减少网络的参数量与计算量，如上图b所示。
备注举例：假如前一层的输出为100x100x128，经过具有256个5x5卷积核的卷积层之后（stride=1, pad=2）, 输出数据为100x100x256.其中，卷积层的参数为5x5x128x256+256。例如上一层输出先经过具有32个1x1卷积核的卷积层（1x1卷积降低了通道数，且特征图尺寸不变），经过具有256个5x5卷积核的卷积层，最终的输出数据仍为100x100x256，但卷积参数量以及减少为(128x1x1x32+32)+(32x5x5x256+256)，参数数量减少为原来的约四分之一。其计算量由原先的8.191x10e9，降低至2.048x10e9。
1x1卷积核的作用：1x1卷积核的最大作用是降低输入特征图的通道数，减少 网络的参数量与计算量。
最后Inception Module基本由1x1卷积，3x3卷积，5x5卷积，3x3最大池化四个基本单元组成，对四个基本单元运算结果进行通道上组合，不同大小的卷积核赋予不同大小的感受野，从而提取到图像不同尺度的信息，进行融合，得到图像更好的表征，就是Inception Module的核心思想。
实现的Inception v1网络结构图如下所示：
注： 另外增加了两个辅助分支，作用有两点：
- 避免梯度消失，用于前向传导梯度。反向传播时，如果有一层求导为0，链式求导结果则为0。
- 将中间某一层输出用作分类，起到模型融合作用，实际测试时，这两个辅助softmax分支会被去掉。 在后续模型的发展中，该方法采用较少。
大部分流行的CNN是将网络的卷积层堆叠的越来越多，网络越来越深，同时channel越来越宽，网络越来越宽，以此来希望提取更高层的特征，从而得到更好的性能。但单纯的网络堆叠和加宽会带来副作用，包括梯度爆炸和数据量剧增而导致的训练困难的问题等。而Inception的提出，改善了此种现象。