目录
[1 导入数据集](#1 导入数据集)
[2 使用tensorboard展示经过各个层的图片数据](#2 使用tensorboard展示经过各个层的图片数据)
[3 完整的模型训练测试流程](#3 完整的模型训练测试流程)
[4 加载训练好的模型进行测试](#4 加载训练好的模型进行测试)
1 导入数据集
python
import torch
from torch.utils.data import DataLoader
import torchvision
from torchvision import transforms
import torch.nn as nn
# 准备数据集
from torch.utils.tensorboard import SummaryWriter
train_data = torchvision.datasets.CIFAR10('./data', train=True, transform=transforms.ToTensor(), download=True)
print("train数据", train_data)
print(f"train_data数据的长度是{len(train_data)}")
train_data = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
print("------------------------------------------")
test_data = torchvision.datasets.CIFAR10('./data', train=False, transform=transforms.ToTensor(), download=True)
print("test数据", test_data)
print(f"test_data数据的长度是{len(test_data)}")
print("第一条数据",test_data[0])
test_data = DataLoader(dataset=test_data, batch_size=64, shuffle=True)
train数据 Dataset CIFAR10
Number of datapoints: 50000
Root location: ./data
Split: Train
StandardTransform
Transform: ToTensor()
train_data数据的长度是50000
Files already downloaded and verified
test数据 Dataset CIFAR10
Number of datapoints: 10000
Root location: ./data
Split: Test
StandardTransform
Transform: ToTensor()
test_data数据的长度是10000
第一条数据 (tensor(\[\[0.6196, 0.6235, 0.6471, ..., 0.5373, 0.4941, 0.4549,
0.5961, 0.5922, 0.6235, ..., 0.5333, 0.4902, 0.4667,
0.5922, 0.5922, 0.6196, ..., 0.5451, 0.5098, 0.4706,
...,
0.2667, 0.1647, 0.1216, ..., 0.1490, 0.0510, 0.1569,
0.2392, 0.1922, 0.1373, ..., 0.1020, 0.1137, 0.0784,
0.2118, 0.2196, 0.1765, ..., 0.0941, 0.1333, 0.0824],
\[0.4392, 0.4353, 0.4549, ..., 0.3725, 0.3569, 0.3333,
0.4392, 0.4314, 0.4471, ..., 0.3725, 0.3569, 0.3451,
0.4314, 0.4275, 0.4353, ..., 0.3843, 0.3725, 0.3490,
2 使用tensorboard展示经过各个层的图片数据
python
class convModel(nn.Module):
def __init__(self):
super(convModel, self).__init__()
self.conv1 = nn.Conv2d(in_channels=3, out_channels=6, stride=1, padding=0, bias=True, padding_mode='zeros', kernel_size=3)
def forward(self, input_data):
return self.conv1(input_data)
write = SummaryWriter('convModel')
model = convModel()
for batch_id, data in enumerate(test_data):
write.add_images('原始图片数据展示', data[0], dataformats='NCHW', global_step=batch_id)
input_data, label = data[0],data[1]
print("batchSize",input_data.size(0))
output_data = model(input_data)
# 因为经过卷积之后,通道数变为6了,而add_images的源码中要求的通道个数是4个,所以要进行通道变换
output_shape_data = torch.reshape(output_data,(-1,3,30,30))
write.add_images('经过卷积层之后的图片数据展示', output_shape_data, global_step=batch_id)
if batch_id % 300 == 0:
print("原始数据的形状", input_data.shape)
print("经过卷积层之后的形状", output_data.shape)
print("经过形状改变之后", output_shape_data.shape)
write.close()
batchSize 64
原始数据的形状 torch.Size(64, 3, 32, 32)
经过卷积层之后的形状 torch.Size(64, 6, 30, 30)
经过形状改变之后 torch.Size(128, 3, 30, 30)
batchSize 64
batchSize 64
batchSize 64
batchSize 64
batchSize 64
batchSize 64
batchSize 64
python
class maxPoolingModel(nn.Module):
def __init__(self):
super(maxPoolingModel, self).__init__()
self.MaxPool2d = nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=False)
def forward(self, input_data):
return self.MaxPool2d(input_data)
write = SummaryWriter('maxPoolingModel')
model = maxPoolingModel()
for batch_id, data in enumerate(test_data):
write.add_images('原始图片数据展示', data[0], dataformats='NCHW', global_step=batch_id)
input_data, label = data[0],data[1]
output_data = model(input_data)
write.add_images('经过池化层之后的图片数据展示', output_data, global_step=batch_id)
if batch_id % 300 == 0:
print("原始数据的形状", input_data.shape)
print("经过池化层之后的形状", output_data.shape)
write.close()
原始数据的形状 torch.Size(64, 3, 32, 32)
经过池化层之后的形状 torch.Size(64, 3, 16, 16)
python
class unLineModel(nn.Module):
def __init__(self):
super(unLineModel, self).__init__()
self.sigmoid = nn.Sigmoid()
def forward(self, input_data):
return self.sigmoid(input_data)
write = SummaryWriter('unLineModel')
model = unLineModel()
for batch_id, data in enumerate(test_data):
write.add_images('原始图片数据展示', data[0], dataformats='NCHW', global_step=batch_id)
input_data, label = data[0],data[1]
output_data = model(input_data)
write.add_images('经过非线性层之后的图片数据展示', output_data, global_step=batch_id)
if batch_id % 300 == 0:
print("原始数据的形状", input_data.shape)
print("经过非线性层之后的形状", output_data.shape)
write.close()
原始数据的形状 torch.Size(64, 3, 32, 32)
经过非线性层之后的形状 torch.Size(64, 3, 32, 32)
3 完整的模型训练测试流程
python
class Model(nn.Module):
def __init__(self):
super(Model,self).__init__()
self.model = nn.Sequential(
nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2,stride=1),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2,stride=1),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2,stride=1),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Flatten(),
nn.Linear(in_features=1024, out_features=64),
nn.Linear(in_features=64, out_features=10)
)
def forward(self, batch_data):
return self.model(batch_data)
# 第一种方式:使用cuda,只需要给模型、损失函数、训练数据、测试数据调用cuda即可,但是这种情况下必须使用if torch.cuda.is_available():判断是否存在cuda,没有的话还是使用cpu,但是没有使用torch.cuda.is_available()判断的话会出错,导致程序无法运行
# 第二种方式:cuda:0 单个显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else 'cpu')
model = Model()
model.to(device=device)
print(model)
batch_data = torch.ones((64,3,32,32)).to(device)
output = model(batch_data)
print("output.shape", output.shape)
Model(
(model): Sequential(
(0): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(4): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
(5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(6): Flatten(start_dim=1, end_dim=-1)
(7): Linear(in_features=1024, out_features=64, bias=True)
(8): Linear(in_features=64, out_features=10, bias=True)
使用Gpu训练的两种方式
# 第一种方式:使用cuda,只需要给模型、损失函数、训练数据、测试数据调用cuda即可,但是这种情况下必须使用if torch.cuda.is_available():判断是否存在cuda,没有的话还是使用cpu,但是没有使用torch.cuda.is_available()判断的话会出错,导致程序无法运行 # 第二种方式:cuda:0 单个显卡 device = torch.device("cuda:0" if torch.cuda.is_available() else 'cpu'),在这种情况写,只需要将对应的模型、损失函数、训练数据、测试数据使用to调用device上即可
使用tensorboard显示模型
python
from torch.utils.tensorboard import SummaryWriter
write = SummaryWriter('model')
write.add_graph(model=model,input_to_model=batch_data)
write.close()
模型训练测试
python
# -------------------------CrossEntropyLoss()维度要求的底层源码-------------------
# Shape:
# - Input: :math:`(N, C)` where `C = number of classes`, or
# :math:`(N, C, d_1, d_2, ..., d_K)` with :math:`K \geq 1`
# in the case of `K`-dimensional loss.
# - Target: :math:`(N)` where each value is :math:`0 \leq \text{targets}[i] \leq C-1`, or
# :math:`(N, d_1, d_2, ..., d_K)` with :math:`K \geq 1` in the case of
# K-dimensional loss.
# - Output: scalar.
# If :attr:`reduction` is ``'none'``, then the same size as the target:
# :math:`(N)`, or
# :math:`(N, d_1, d_2, ..., d_K)` with :math:`K \geq 1` in the case
# of K-dimensional loss.
criteria = nn.CrossEntropyLoss()
criteria.to(device)
nn.L1Loss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
sum_loss_list = []
epoch_list = []
from torch.utils.tensorboard import SummaryWriter
write = SummaryWriter("figure")
total_train_step = 0
total_test_step = 0
for epoch in range(50):
ever_epoch_loss_sum = 0.0
print("---------------------第 {} 轮训练开始---------------------".format(epoch+1))
model.train()
for batch_id, data in enumerate(train_data):
input_data, input_label = data
input_data = input_data.to(device)
input_label = input_label.to(device)
output_data = model(input_data)
# if batch_id%300 == 0:
# print("input_data", input_data.shape) # input_data torch.Size([64, 3, 32, 32])
# print("output_data", output_data.shape) # output_data torch.Size([64, 10])
# print("input_label", input_label.shape) # input_label torch.Size([64])
loss = criteria(output_data, input_label)
ever_epoch_loss_sum = ever_epoch_loss_sum + loss.item()
loss.backward()
optimizer.step()
optimizer.zero_grad()
if total_train_step % 200 == 0:
print("当前总的训练次数:{} ,每一次的Loss:{}".format(total_train_step, loss.item()))
write.add_scalar('train_loss', loss.item(), total_train_step)
total_train_step = total_train_step + 1
sum_loss_list.append(ever_epoch_loss_sum)
epoch_list.append(epoch)
print("---------------------第 {} 轮测试开始---------------------".format(epoch+1))
model.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for batch_id, data in enumerate(test_data):
images, label = data
images = images.to(device)
label = label.to(device)
output = model(images)
loss = criteria(output,label)
total_test_loss = total_test_loss + loss.item()
accuracy = (output.argmax(1) == label).sum()
total_accuracy = total_accuracy + accuracy
print("整体测试集上的Loss: {}".format(total_test_loss))
print("整体数据集上的正确率:{}".format(total_accuracy/len(test_data)))
write.add_scalar("test_accuracy",total_accuracy/len(test_data),total_test_step)
write.add_scalar('test_loss', total_test_loss, total_test_step)
total_test_step = total_test_step + 1
torch.save(model,'model_{}.pth'.format(epoch))
print("保存第 {} 轮模型".format(epoch+1))
write.close()
L1Loss函数
python
inputs = torch.tensor([1,2,3], dtype=torch.float32)
print("原始数据inputs", inputs)
print("原始数据形状inputs.shape", inputs.shape)
targets = torch.tensor([1,2,5], dtype=torch.float32)
print("目标数据targets", targets)
print("目标数据形状targets.shape", targets.shape)
inputs = torch.reshape(inputs,(1,-1))
print("形状改变数据inputs", inputs)
print("形状改变数据形状inputs.shape", inputs.shape)
targets = torch.reshape(targets,(1,-1))
print("目标数据改变targets", targets)
print("目标数据形状改变targets.shape", targets.shape)
loss = nn.L1Loss()
# - Input: :math:`(N, *)` where :math:`*` means, any number of additional
# dimensions
# - Target: :math:`(N, *)`, same shape as the input
result = loss(inputs, targets)
print(result)
原始数据inputs tensor(1., 2., 3.)
原始数据形状inputs.shape torch.Size(3)
目标数据targets tensor(1., 2., 5.)
目标数据形状targets.shape torch.Size(3)
形状改变数据inputs tensor(\[1., 2., 3.])
形状改变数据形状inputs.shape torch.Size(1, 3)
目标数据改变targets tensor(\[1., 2., 5.])
目标数据形状改变targets.shape torch.Size(1, 3)
tensor(0.6667)
保存未训练模型或者已经训练完的模型
python
# 模型的保存
torch.save(model,'class_model.pth')
# 模型加载,但是这种情况下如果加载的模型和原本的模型没有在同一个文件中,那么需要将原本的模型使用from加载到当前文件中,再使用torch.load
model = torch.load('class_model.pth')
print(model)
4 加载训练好的模型进行测试
python
import torch.nn as nn
import torch
class Model(nn.Module):
def __init__(self):
super(Model,self).__init__()
self.model = nn.Sequential(
nn.Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2,stride=1),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2,stride=1),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2,stride=1),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Flatten(),
nn.Linear(in_features=1024, out_features=64),
nn.Linear(in_features=64, out_features=10)
)
def forward(self, batch_data):
return self.model(batch_data)
load_model = torch.load('G:\python_files\深度学习代码库\model_49.pth') # 加载模型,使用上面的非字典形式保存的模型,这个时候加载的时候必须把原本定义的模型加载到当前文件,然后使用该函数加载。同时需要注意,如果加载的模型原本是在cuda上跑的,这个时候要将模型使用load函数的参数map_location=torch.device('cpu')加载到cpu上,或者也可以将图片的数据放入到gpu上,与原本的模型对应起来
from torchvision import transforms
from PIL import Image
image = Image.open('G:\python_files\深度学习代码库\cats\cat\cat.10.jpg')
trans = transforms.Compose([transforms.Resize((32,32)),transforms.ToTensor()])
trans_image_tensor = trans(image)
# 因为上面的模型训练的时候输入是(NCHW),所以将训练完的模型加载进来使用测试的时候必须要将一张图片reshape模型需要的形状,否则就会报错
tensor_shape = torch.reshape(trans_image_tensor,(1,3,32,32)).to(torch.device("cuda:0"))
load_model.eval()
with torch.no_grad():
output = load_model(tensor_shape)
print(output)
注意事项:
load_model = torch.load('G:\python_files\深度学习代码库\model_49.pth') # 加载模型,使用上面的非字典形式保存的模型,这个时候加载的时候必须把原本定义的模型加载到当前文件,然后使用该函数加载。同时需要注意,如果加载的模型原本是在cuda上跑的,这个时候要将模型使用load函数的参数map_location=torch.device('cpu')加载到cpu上,或者也可以将图片的数据放入到gpu上,与原本的模型对应起来
# 因为上面的模型训练的时候输入是(NCHW),所以将训练完的模型加载进来使用测试的时候必须要将一张图片reshape模型需要的形状,否则就会报错 tensor_shape = torch.reshape(trans_image_tensor,(1,3,32,32)).to(torch.device("cuda:0"))