pytorch官網教程+注釋

Classifier

import torch 
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=3,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=3,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

Files already downloaded and verified
Files already downloaded and verified

import matplotlib.pyplot as plt
import numpy as np
def imshow(img):
    img = img/2 + 0.5 # 因為之前標准化的時候除以0.5就是乘以2，還減了0.5，所以回復原來的亮度值
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg,(1,2,0))) #  c,h,w -> h,w,c 
    plt.show()
dataiter = iter(trainloader)
images,labels = dataiter.next()
print(images.shape) #torch.Size([4, 3, 32, 32]) bchw
print(torchvision.utils.make_grid(images).shape) #torch.Size([3, 36, 138])
#imshow(torchvision.utils.make_grid(images)) # 以格子形式顯示多張圖片
#print(" ".join("%5s"% classes[labels[j]] for j in range(4)))

torch.Size([3, 3, 32, 32])
torch.Size([3, 36, 104])

import torch.nn as nn
import torch.nn.functional as F
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
net = Net()

import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(),lr = 0.001,momentum = 0.9)

for epoch in range(2):
    running_loss = 0.0
    for i,data in enumerate(trainloader):
        inputs,labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs,labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if i%2000 ==1999:
            print('[%d,%5d] loss:%.3f'%(epoch+1,i+1,running_loss/2000))
            running_loss = 0.0
print("finished training")

[1, 2000] loss:1.468
[1, 4000] loss:1.410
[1, 6000] loss:1.378
[1, 8000] loss:1.363
[1,10000] loss:1.330
[1,12000] loss:1.299
[2, 2000] loss:1.245
[2, 4000] loss:1.217
[2, 6000] loss:1.237
[2, 8000] loss:1.197
[2,10000] loss:1.193
[2,12000] loss:1.196
finished training

dataiter = iter(testloader)
images,labels = dataiter.next()
imshow(torchvision.utils.make_grid(images))

outputs = net(images)
_,predicted = torch.max(outputs,1)
print("predicted"," ".join([classes[predicted[j]] for j in range(4)]))

predicted cat ship ship ship

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images,labels = data
        outputs = net(images)
        _,predicted = torch.max(outputs.data,1)
        total += labels.size(0) # 等價於labels.size()[0]
        correct+= (predicted==labels).sum().item()
print("acc:{}%%".format(100*correct/total))

acc:56.96%%

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

print(device)

cpu

net.to(device)

Net(
  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

DataLoading And Processing

from __future__ import print_function,division
import os
import torch
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset,DataLoader
from torchvision import transforms,utils
import warnings
from skimage import io,transform
warnings.filterwarnings("ignore")
plt.ion()

landmarks_frame = pd.read_csv("data/faces/face_landmarks.csv") # name x y x y ...
#print(landmarks_frame.columns.tolist())
n = 65 # 第65個樣本
img_name = landmarks_frame.iloc[n,0]# 第65個樣本的文件名
#print(img_name)
#print(landmarks_frame.iloc[n,1:])
landmarks = landmarks_frame.iloc[n,1:].as_matrix()# 第65個樣本的樣本值向量
#如果不加上as_matrix的結果就是feature name + feature val，加了之后只有feature val
#print(landmarks)
landmarks = landmarks.astype('float').reshape(-1,2) # 兩個一組，組成兩列的矩陣

def show_landmarks(image,landmarks):
    plt.imshow(image)
    plt.scatter(landmarks[:,0],landmarks[:,1],s=10,marker='.',c='r')
    #plt.pause(0.001) # python 窗口用得着

plt.figure()
show_landmarks(io.imread(os.path.join("data/faces/",img_name)),landmarks)

# torch.utils.data.Dataset 是一個抽象類，我們的dataset需要繼承這個類，才能對其進行操作
class FaceLandmarksDataset(Dataset):
    def __init__(self,csv_file,root_dir,transform=None):
        self.landmarks_frame = pd.read_csv(csv_file)
        self.root_dir = root_dir
        self.transform = transform
    def __len__(self):
        return len(self.landmarks_frame)
    def __getitem__(self,idx):
        img_name = os.path.join(
            self.root_dir,
            self.landmarks_frame.iloc[idx,0]
        )
        image = io.imread(img_name)
        landmarks = self.landmarks_frame.iloc[idx,1:].as_matrix()
        landmarks = landmarks.astype('float').reshape([-1,2])
        sample = {"image":image,"landmarks":landmarks}
        if self.transform:
            sample = self.transform(sample)
        return sample

face_dataset = FaceLandmarksDataset(csv_file='data/faces/face_landmarks.csv',root_dir='data/faces/')
fig = plt.figure()
for i in range(len(face_dataset)):
    sample = face_dataset[i]
    print(i,sample['image'].shape,sample['landmarks'].shape)
    ax = plt.subplot(1,4,i+1)
    #plt.tight_layout()
    ax.set_title("sample #{}".format(i))
    ax.axis("off")
    show_landmarks(**sample) #**為python 拆包，將dict拆解為x=a,y=b的格式
    if i==3:
        plt.show()
        break

0 (324, 215, 3) (68, 2)
1 (500, 333, 3) (68, 2)
2 (250, 258, 3) (68, 2)
3 (434, 290, 3) (68, 2)

class Rescale():
    def __init__(self,output_size):
        assert isinstance(output_size,(int,tuple)) # 必須是int或tuple類型，否則報錯，要習慣用assert isinstance
        self.output_size = output_size
    def __call__(self,sample): # 這個類的對象是一個函數，所以定義call
        image,landmarks = sample['image'],sample['landmarks']
        h,w = image.shape[:2]
        if isinstance(self.output_size,int): # 如果只輸入了一個值，則以較短邊為基准保持長寬比率不變變換
            if h>w:
                new_h,new_w = self.output_size*h/w,self.output_size
            else:
                new_h,new_w = self.output_size,self.output_size*w/h
        else: #給定一個size那就直接變成這個size
            new_h,new_w = output_size
        new_h,new_w = int(new_h),int(new_w)
        img = transform.resize(image,(new_h,new_w)) # 進行resize操作，調用的是skimage的resize，提供(h,w)，跟opencv相反
        landmarks = landmarks * [new_w/w,new_h/h]# 相應的，landmark也要做轉換
        return {"image":img,"landmarks":landmarks} # 返回dict
class RandomCrop():
    def __init__(self,output_size):
        assert isinstance(output_size,(int,tuple))
        if isinstance(output_size,int):
            self.output_size = (output_size,output_size)
        else:
            assert len(output_size) ==2
            self.output_size = output_size
    def __call__(self,sample):
        image,landmarks = sample['image'],sample['landmarks']
        h,w = image.shape[:2]# 原圖寬高
        new_h,new_w = self.output_size # 裁剪的寬高
        top = np.random.randint(0,h-new_h) # 裁剪輸出圖像最上端
        left = np.random.randint(0,w-new_w) # 最左端，保證取的時候不越界
        image = image[top:top+new_h,left:left+new_w] # 隨機裁剪
        landmarks = landmarks - [left,top] # 這里landmarks同樣也需要做變換,之所以減去[left,top]是因為存儲的是x,y對應的軸是w軸和h軸
        return {"image":image,"landmarks":landmarks}
class ToTensor():
    def __call__(self,sample):
        image,landmarks = sample['image'],sample['landmarks']
        image = image.transpose((2,0,1)) # transpose實質是reshape
        # skimage的shape [h,w,c]
        # torch的shape [c,h,w]
        return {"image":torch.from_numpy(image),"landmarks":torch.from_numpy(landmarks)}

scale = Rescale(256)
crop = RandomCrop(128)
composed = transforms.Compose([Rescale(256),RandomCrop(224)]) # 組合變換
fig = plt.figure()
sample = face_dataset[65]
for i,tsfrm in enumerate([scale,crop,composed]): # 三種變換
    transformed_sample = tsfrm(sample) # 應用其中之一 
    ax = plt.subplot(1,3,i+1)
    plt.tight_layout()
    show_landmarks(**transformed_sample)
plt.show()

transformed_dataset = FaceLandmarksDataset(csv_file = 'data/faces/face_landmarks.csv',
                                           root_dir="data/faces/",
                                           transform=transforms.Compose(
                                               [
                                                   Rescale(256),
                                                   RandomCrop(224),
                                                   ToTensor()
                                               ])
                                          )
for i in range(len(transformed_dataset)):
    sample = transformed_dataset[i]
    print(i,sample['image'].size(),sample['landmarks'].size())
    if i==3:
        break

0 torch.Size([3, 224, 224]) torch.Size([68, 2])
1 torch.Size([3, 224, 224]) torch.Size([68, 2])
2 torch.Size([3, 224, 224]) torch.Size([68, 2])
3 torch.Size([3, 224, 224]) torch.Size([68, 2])

dataloader = DataLoader(transformed_dataset,batch_size=4,shuffle=True,num_workers=4) # 調用dataloader
def show_landmarks_batch(sample_batched):
    images_batch,landmarks_batch = sample_batched['image'],sample_batched['landmarks']
    batch_size = len(images_batch)
    im_size = images_batch.size(2) #這里的size是shape
    grid = utils.make_grid(images_batch) # 多張圖變成一張圖
    plt.imshow(grid.numpy().transpose(1,2,0)) # reshape到能用plt顯示
    for i in range(batch_size):
        # 第i張圖片的所有點的x，所有點的y，后面 + i*im_size是由於所有圖像水平顯示，所以需要水平有個偏移
        # 轉numpy是因為torch類型的數據沒辦法scatter
        plt.scatter(landmarks_batch[i,:,0].numpy() + i*im_size,
                   landmarks_batch[i,:,1].numpy(),
                   s=10,marker='.',c='r')
        plt.title("batch from dataloader")
for i_batch,sample_batched in enumerate(dataloader):
    if i_batch ==3:
        plt.figure()
        show_landmarks_batch(sample_batched)
        plt.axis("off") # 關閉坐標系
        plt.ioff()
        plt.show()
        break

<built-in method size of Tensor object at 0x7f273f3bad38>