>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**
Pycharm代码如下：
import torch
import torch.nn as nn
from torchvision import transforms, datasets
import pathlib, warnings
warnings.filterwarnings("ignore") # 忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data_dir = 'D:/研究生课题/深度学习-代码/11-data/bird_photos'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[5] for path in data_paths]
print(classeNames)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：", image_count)
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("D:/研究生课题/深度学习-代码/11-data/bird_photos", 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
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
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
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
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, 4) # 4是识别种类的数目
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)
print(model)
import torchsummary as summary
summary.summary(model, (3, 224, 224))
# 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
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):
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)
# 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')
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()
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}')
predict_one_image(image_path='D:/研究生课题/深度学习-代码/11-data/bird_photos/Bananaquit/007.jpg',
model=model,
transform=train_transforms,
classes=classes)
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
print(epoch_test_acc, epoch_test_loss)
print(epoch_test_acc)
运行结果如下：
C:\Users\dell\anaconda3\envs\pytorch-gpu\python.exe D:\pythonProject5\trains.py
['Bananaquit', 'Black Skimmer', 'Black Throated Bushtiti', 'Cockatoo']
图片总数为： 565
{'Bananaquit': 0, 'Black Skimmer': 1, 'Black Throated Bushtiti': 2, 'Cockatoo': 3}
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64
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)
)
----------------------------------------------------------------
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
----------------------------------------------------------------
Epoch: 1, Train_acc:37.4%, Train_loss:1.365, Test_acc:25.7%, Test_loss:1.546, Lr:1.00E-04
Epoch: 2, Train_acc:70.4%, Train_loss:0.879, Test_acc:34.5%, Test_loss:1.736, Lr:1.00E-04
Epoch: 3, Train_acc:78.1%, Train_loss:0.641, Test_acc:54.9%, Test_loss:1.079, Lr:1.00E-04
Epoch: 4, Train_acc:83.6%, Train_loss:0.427, Test_acc:69.0%, Test_loss:1.022, Lr:1.00E-04
Epoch: 5, Train_acc:87.6%, Train_loss:0.358, Test_acc:45.1%, Test_loss:2.796, Lr:1.00E-04
Epoch: 6, Train_acc:84.7%, Train_loss:0.373, Test_acc:60.2%, Test_loss:2.051, Lr:1.00E-04
Epoch: 7, Train_acc:88.1%, Train_loss:0.346, Test_acc:61.9%, Test_loss:1.014, Lr:1.00E-04
Epoch: 8, Train_acc:91.2%, Train_loss:0.237, Test_acc:74.3%, Test_loss:0.785, Lr:1.00E-04
Epoch: 9, Train_acc:92.7%, Train_loss:0.187, Test_acc:75.2%, Test_loss:0.877, Lr:1.00E-04
Epoch:10, Train_acc:93.6%, Train_loss:0.180, Test_acc:77.9%, Test_loss:0.774, Lr:1.00E-04
Done
预测结果是：Bananaquit
0.7876106194690266 0.6938939392566681
0.7876106194690266
进程已结束，退出代码为 0
总结：
ResNet-50通过引入残差块，解决了随着网络深度增加梯度消失的问题。残差学习使得训练非常深的网络成为可能。ResNet-50 是 50 层的网络，比之前的浅层网络能更好地捕捉复杂特征，同时避免了训练难度的急剧增加。
扫一扫
2831
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
