深度学习第J6周：ResNeXt-50实战解析
| 阿里云国内75折 回扣 微信号：monov8 |
| 阿里云国际，腾讯云国际，低至75折。AWS 93折 免费开户实名账号 代冲值 优惠多多 微信号：monov8 飞机：@monov6 |
目录
本文为[365天深度学习训练营]内部限免文章版权归 *K同学啊* 所有
作者[K同学啊]
本周任务
●阅读ResNeXt论文了解作者的构建思路
●对比我们之前介绍的ResNet50V2、DenseNet算法
●使用ResNeXt-50算法完成猴痘病识别
一、模型结构介绍
ResNeXt是由何凯明团队在2017年CVPR会议上提出来的新型图像分类网络。ResNeXt是ResNet的升级版在ResNet的基础上引入了cardinality的概念类似于ResNetResNeXt也有ResNeXt-50ResNeXt-101的版本。ResNeXt论文名为Aggregated Residual Transformations for Deep Neural Networks.pdf
这篇文章介绍了一种用于图像分类的简单而有效的网络架构称为Aggregated Residual Transformations for Deep Neural Networks。该网络采用了VGG/ResNets的策略通过重复层来增加深度和宽度并利用分裂-变换-合并策略以易于扩展的方式进行转换。文章还提出了一个新的维度——“基数”它是指转换集合的大小可以在保持复杂性不变的情况下提高分类准确性。作者在ImageNet-1K数据集上进行了实证研究证明了这种方法的有效性。
下图是ResNet左与ResNeXt右block的差异。在ResNet中输入的具有256个通道的特征经过1×1卷积压缩4倍到64个通道之后3×3的卷积核用于处理特征经1×1卷积扩大通道数与原特征残差连接后输出。
ResNeXt也是相同的处理策略但在ResNeXt中输入的具有256个通道的特征被分为32个组每组被压缩64倍到4个通道后进行处理。32个组相加后与原特征残差连接后输出。这里cardinatity指的是一个block中所具有的相同分支的数目。
分组卷积
ResNeXt中采用的分组卷机简单来说就是将特征图分为不同的组再对每组特征图分别进行卷积这个操作可以有效的降低计算量。
在分组卷积中每个卷积核只处理部分通道比如下图中红色卷积核只处理红色的通道绿色卷积核只处理绿色通道黄色卷积核只处理黄色通道。此时每个卷积核有2个通道每个卷积核生成一张特征图。
总结来说就是ResNeXt-50网络简单讲就是在ResNet结构的基础上采用了聚合残差结构和局部连接结构同时引入了Random Erasing和Mixup等数据增强和正则化方法。
二、前期准备
大致模板和以前一样以后不再详细列样例可见深度学习第J4周ResNet与DenseNet结合探索_牛大了2023的博客-CSDN博客
配置gpu+导入数据集
import os,PIL,random,pathlib
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
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)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为", image_count)数据预处理+划分数据集
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。
])
test_transform = 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("./data/", transform=train_transforms)
print(total_data.class_to_idx)
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])
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
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
三、模型
class BN_Conv2d(nn.Module):
"""
BN_CONV_RELU
"""
def __init__(self, in_channels, out_channels, kernel_size, stride, padding, dilation=1, groups=1, bias=False):
super(BN_Conv2d, self).__init__()
self.seq = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride,
padding=padding, dilation=dilation, groups=groups, bias=bias),
nn.BatchNorm2d(out_channels)
)
def forward(self, x):
return F.relu(self.seq(x))
class ResNeXt_Block(nn.Module):
"""
ResNeXt block with group convolutions
"""
def __init__(self, in_chnls, cardinality, group_depth, stride):
super(ResNeXt_Block, self).__init__()
self.group_chnls = cardinality * group_depth
self.conv1 = BN_Conv2d(in_chnls, self.group_chnls, 1, stride=1, padding=0)
self.conv2 = BN_Conv2d(self.group_chnls, self.group_chnls, 3, stride=stride, padding=1, groups=cardinality)
self.conv3 = nn.Conv2d(self.group_chnls, self.group_chnls*2, 1, stride=1, padding=0)
self.bn = nn.BatchNorm2d(self.group_chnls*2)
self.short_cut = nn.Sequential(
nn.Conv2d(in_chnls, self.group_chnls*2, 1, stride, 0, bias=False),
nn.BatchNorm2d(self.group_chnls*2)
)
def forward(self, x):
out = self.conv1(x)
out = self.conv2(out)
out = self.bn(self.conv3(out))
out += self.short_cut(x)
return F.relu(out)
class ResNeXt(nn.Module):
"""
ResNeXt builder
"""
def __init__(self, layers: object, cardinality, group_depth, num_classes) -> object:
super(ResNeXt, self).__init__()
self.cardinality = cardinality
self.channels = 64
self.conv1 = BN_Conv2d(3, self.channels, 7, stride=2, padding=3)
d1 = group_depth
self.conv2 = self.___make_layers(d1, layers[0], stride=1)
d2 = d1 * 2
self.conv3 = self.___make_layers(d2, layers[1], stride=2)
d3 = d2 * 2
self.conv4 = self.___make_layers(d3, layers[2], stride=2)
d4 = d3 * 2
self.conv5 = self.___make_layers(d4, layers[3], stride=2)
self.fc = nn.Linear(self.channels, num_classes) # 224x224 input size
def ___make_layers(self, d, blocks, stride):
strides = [stride] + [1] * (blocks-1)
layers = []
for stride in strides:
layers.append(ResNeXt_Block(self.channels, self.cardinality, d, stride))
self.channels = self.cardinality*d*2
return nn.Sequential(*layers)
def forward(self, x):
out = self.conv1(x)
out = F.max_pool2d(out, 3, 2, 1)
out = self.conv2(out)
out = self.conv3(out)
out = self.conv4(out)
out = self.conv5(out)
out = F.avg_pool2d(out, 7)
out = out.view(out.size(0), -1)
out = F.softmax(self.fc(out),dim=1)
return out# 定义完成测试一下
model = ResNeXt([3, 4, 6, 3], 32, 4, 4)
model.to(device)
# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))
三、训练运行
3.1训练
代码和以前的差不多不再细说
# 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
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跑十轮并保存模型
import copy
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 10
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
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))
# 保存最佳模型到文件中
PATH = './best_model.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
print('Done')
打印训练记录图
import matplotlib.pyplot as plt
# 隐藏警告
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
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()
3.2指定图片进行预测
把训练部分注释掉
from PIL import Image
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) # 展示预测的图片
test_img = transform(test_img)
img = test_img.to(device).unsqueeze(0)
model.eval()
output = model(img)
_, 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/Others/NM01_01_01.jpg',
model=model,
transform=train_transforms,
classes=classes)