【第一部分】 视频学习心得及问题总结
【第二部分】 代码练习
2.1 MNIST 数据集分类
- 首先 先import~
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import matplotlib.pyplot as plt
import numpy
# 一个函数，用来计算模型中有多少参数
def get_n_params(model):
np=0
for p in list(model.parameters()):
np += p.nelement()
return np
# 使用GPU训练，可以在菜单 "代码执行工具" -> "更改运行时类型" 里进行设置
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
- 导入数据
pytorch内置了MNIST数据集，通过torchvision.datasets 下载即可
torchvision.datasets.MNIST(root, train=True, transform=None, target_transform=None, download=False)
root 为数据集下载到本地后的根目录，包括 training.pt 和 test.pt 文件
train，如果设置为True，从training.pt创建数据集，否则从test.pt创建。
download，如果设置为True, 从互联网下载数据并放到root文件夹下
transform, 一种函数或变换，输入PIL图片，返回变换之后的数据。
target_transform 一种函数或变换，输入目标，进行变换
input_size = 28*28 # MNIST上的图像尺寸是 28x28
output_size = 10 # 类别为 0 到 9 的数字，因此为十类
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('./data', train=True, download=True,
transform=transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('./data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=1000, shuffle=True)
- 创建网络
这一部分之前有点迷 看了看别人的博客，感觉清晰了一点~ https://blog.csdn.net/alxe_made/article/details/84424577
主要是要继承nn.Moudle这个类，然后重写init和 forward方法；init定义了网络有那些层，forward（）定义了网络是怎么连接的
nn.Linear部分的官方文档--》https://pytorch.org/docs/master/generated/torch.nn.Linear.html#torch.nn.Linear
nn.Sequential部分的官方文档--》 https://pytorch.org/docs/master/generated/torch.nn.Sequential.html#torch.nn.Sequential
class FC2Layer(nn.Module):
def __init__(self, input_size, n_hidden, output_size):
# nn.Module子类的函数必须在构造函数中执行父类的构造函数
# 下式等价于nn.Module.__init__(self)
super(FC2Layer, self).__init__()
self.input_size = input_size
# 这里直接用 Sequential 就定义了网络，注意要和下面 CNN 的代码区分开
self.network = nn.Sequential(
nn.Linear(input_size, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, output_size),
nn.LogSoftmax(dim=1)
)
def forward(self, x):
# view一般出现在model类的forward函数中，用于改变输入或输出的形状
# x.view(-1, self.input_size) 的意思是多维的数据展成二维
# 代码指定二维数据的列数为 input_size=784，行数 -1 表示我们不想算，电脑会自己计算对应的数字
# 在 DataLoader 部分，我们可以看到 batch_size 是64，所以得到 x 的行数是64
# 大家可以加一行代码：print(x.cpu().numpy().shape)
# 训练过程中，就会看到 (64, 784) 的输出，和我们的预期是一致的
# forward 函数的作用是，指定网络的运行过程，这个全连接网络可能看不啥意义，
# 下面的CNN网络可以看出 forward 的作用。
x = x.view(-1, self.input_size)
return self.network(x)
class CNN(nn.Module):
def __init__(self, input_size, n_feature, output_size):
# 执行父类的构造函数，所有的网络都要这么写
super(CNN, self).__init__()
# 下面是网络里典型结构的一些定义，一般就是卷积和全连接
# 池化、ReLU一类的不用在这里定义
self.n_feature = n_feature
self.conv1 = nn.Conv2d(in_channels=1, out_channels=n_feature, kernel_size=5)
self.conv2 = nn.Conv2d(n_feature, n_feature, kernel_size=5)
self.fc1 = nn.Linear(n_feature*4*4, 50)
self.fc2 = nn.Linear(50, 10)
# 下面的 forward 函数，定义了网络的结构，按照一定顺序，把上面构建的一些结构组织起来
# 意思就是，conv1, conv2 等等的，可以多次重用
def forward(self, x, verbose=False):
x = self.conv1(x)
x = F.relu(x)
x = F.max_pool2d(x, kernel_size=2)
x = self.conv2(x)
x = F.relu(x)
x = F.max_pool2d(x, kernel_size=2)
x = x.view(-1, self.n_feature*4*4)
x = self.fc1(x)
x = F.relu(x)
x = self.fc2(x)
x = F.log_softmax(x, dim=1)
return x
-
训练测试
在全连接网络上训练
卷积神经网络上训练
可以看出 CNN的效果明显好于全连接网络~ -
打乱像素后测试
# 这里解释一下 torch.randperm 函数，给定参数n，返回一个从0到n-1的随机整数排列
perm = torch.randperm(784)
plt.figure(figsize=(8, 4))
for i in range(10):
image, _ = train_loader.dataset.__getitem__(i)
# permute pixels
image_perm = image.view(-1, 28*28).clone()
image_perm = image_perm[:, perm]
image_perm = image_perm.view(-1, 1, 28, 28)
plt.subplot(4, 5, i + 1)
plt.imshow(image.squeeze().numpy(), 'gray')
plt.axis('off')
plt.subplot(4, 5, i + 11)
plt.imshow(image_perm.squeeze().numpy(), 'gray')
plt.axis('off')
再在全连接网络中测试~
CNN中测试
可以看出全连接网络的性能基本上没有发生变化，CNN下降明显
这是因为对于卷积神经网络，会利用像素的局部关系，但是打乱顺序以后，这些像素间的关系将无法得到利用。
2.2 CIFAR10
- 定义网络
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
# 网络放到GPU上
net = Net().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
2.训练测试网络
for epoch in range(10): # 重复多轮训练
for i, (inputs, labels) in enumerate(trainloader):
inputs = inputs.to(device)
labels = labels.to(device)
# 优化器梯度归零
optimizer.zero_grad()
# 正向传播 + 反向传播 + 优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 输出统计信息
if i % 100 == 0:
print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))
print('Finished Training')
# 得到一组图像
images, labels = iter(testloader).next()
# 展示图像
imshow(torchvision.utils.make_grid(images))
# 展示图像的标签
for j in range(8):
print(classes[labels[j]])
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
2.3 使用 VGG16 对 CIFAR10 分类
- 定义网络结构
class VGG(nn.Module):
def __int__(self):
super(VGG, self).__init__()
self.cfg = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M']
self.features = self.make_layers(self.cfg)
self.classifier = nn.Linear(512, 10)
def forward(self, x):
out = self.features(x)
out = out.view(out.size(0), -1)
out = self.classifier(out)
return out
def make_layers(self, cfg):
layers = []
in_channels = 3
for x in cfg:
if x == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1),
nn.BatchNorm2d(x),
nn.ReLU(inplace=True)]
in_channels = x
layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
return nn.Sequential(*layers)
# 网络放到GPU上
net = VGG().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
这一步运行的时候报错了orz 有点迷惑 先记下来
correct = 0
total = 0
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %.2f %%' % (
100 * correct / total))
2.4 猫狗大战
import numpy as np
import matplotlib.pyplot as plt
import os
import torch
import torch.nn as nn
import torchvision
from torchvision import models,transforms,datasets
import time
import json
# 判断是否存在GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print('Using gpu: %s ' % torch.cuda.is_available())
下载、处理数据
! wget http://fenggao-image.stor.sinaapp.com/dogscats.zip
! unzip dogscats.zip
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
vgg_format = transforms.Compose([
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])
data_dir = './dogscats'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
for x in ['train', 'valid']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'valid']}
dset_classes = dsets['train'].classes
loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=64, shuffle=True, num_workers=6)
loader_valid = torch.utils.data.DataLoader(dsets['valid'], batch_size=5, shuffle=False, num_workers=6)
'''
valid 数据一共有2000张图，每个batch是5张，因此，下面进行遍历一共会输出到 400
同时，把第一个 batch 保存到 inputs_try, labels_try，分别查看
'''
count = 1
for data in loader_valid:
print(count, end='\n')
if count == 1:
inputs_try,labels_try = data
count +=1
print(labels_try)
print(inputs_try.shape)
# 显示图片的小程序
def imshow(inp, title=None):
# Imshow for Tensor.
inp = inp.numpy().transpose((1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
inp = np.clip(std * inp + mean, 0,1)
plt.imshow(inp)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
model_vgg = models.vgg16(pretrained=True)
with open('./imagenet_class_index.json') as f:
class_dict = json.load(f)
dic_imagenet = [class_dict[str(i)][1] for i in range(len(class_dict))]
inputs_try , labels_try = inputs_try.to(device), labels_try.to(device)
model_vgg = model_vgg.to(device)
outputs_try = model_vgg(inputs_try)
print(outputs_try)
print(outputs_try.shape)
'''
可以看到结果为5行，1000列的数据，每一列代表对每一种目标识别的结果。
但是我也可以观察到，结果非常奇葩，有负数，有正数，
为了将VGG网络输出的结果转化为对每一类的预测概率，我们把结果输入到 Softmax 函数
'''
m_softm = nn.Softmax(dim=1)
probs = m_softm(outputs_try)
vals_try,pred_try = torch.max(probs,dim=1)
print( 'prob sum: ', torch.sum(probs,1))
print( 'vals_try: ', vals_try)
print( 'pred_try: ', pred_try)
print([dic_imagenet[i] for i in pred_try.data])
imshow(torchvision.utils.make_grid(inputs_try.data.cpu()),
title=[dset_classes[x] for x in labels_try.data.cpu()])
修改最后一层，冻结前面层的参数
print(model_vgg)
model_vgg_new = model_vgg;
for param in model_vgg_new.parameters():
param.requires_grad = False
model_vgg_new.classifier._modules['6'] = nn.Linear(4096, 2)
model_vgg_new.classifier._modules['7'] = torch.nn.LogSoftmax(dim = 1)
model_vgg_new = model_vgg_new.to(device)
print(model_vgg_new.classifier)
训练并测试全连接层
'''
第一步：创建损失函数和优化器
损失函数 NLLLoss() 的 输入 是一个对数概率向量和一个目标标签.
它不会为我们计算对数概率，适合最后一层是log_softmax()的网络.
'''
criterion = nn.NLLLoss()
# 学习率
lr = 0.001
# 随机梯度下降
optimizer_vgg = torch.optim.SGD(model_vgg_new.classifier[6].parameters(),lr = lr)
'''
第二步：训练模型
'''
def train_model(model,dataloader,size,epochs=1,optimizer=None):
model.train()
for epoch in range(epochs):
running_loss = 0.0
running_corrects = 0
count = 0
for inputs,classes in dataloader:
inputs = inputs.to(device)
classes = classes.to(device)
outputs = model(inputs)
loss = criterion(outputs,classes)
optimizer = optimizer
optimizer.zero_grad()
loss.backward()
optimizer.step()
_,preds = torch.max(outputs.data,1)
# statistics
running_loss += loss.data.item()
running_corrects += torch.sum(preds == classes.data)
count += len(inputs)
print('Training: No. ', count, ' process ... total: ', size)
epoch_loss = running_loss / size
epoch_acc = running_corrects.data.item() / size
print('Loss: {:.4f} Acc: {:.4f}'.format(
epoch_loss, epoch_acc))
# 模型训练
train_model(model_vgg_new,loader_train,size=dset_sizes['train'], epochs=1,
# 单次可视化显示的图片个数
n_view = 8
correct = np.where(predictions==all_classes)[0]
from numpy.random import random, permutation
idx = permutation(correct)[:n_view]
print('random correct idx: ', idx)
loader_correct = torch.utils.data.DataLoader([dsets['valid'][x] for x in idx],
batch_size = n_view,shuffle=True)
for data in loader_correct:
inputs_cor,labels_cor = data
# Make a grid from batch
out = torchvision.utils.make_grid(inputs_cor)
imshow(out, title=[l.item() for l in labels_cor])
# 类似的思路，可以显示错误分类的图片，这里不再重复代码
这周学习效率一般，只完成了必做部分 希望接下来能赶上进度=-=