寒假PyTorch工具第五天

课程记录

从模型创建方法到AlexNet

 

---

课程代码

无

 

 

---

作业

1.      采用步进(Step into)的调试方法从创建网络模型开始（net = LeNet(classes=2)）进入到每一个被调用函数，观察net的_modules字段何时被构建并且赋值，记录其中所有进入的类与函数

例如：

第一步：net = LeNet(classes=2)

第二步：LeNet类，__init__()，super(LeNet, self).__init__()

第三步:  Module类, ......

第n步：返回net

略

2.      采用sequential容器，改写Alexnet，给features中每一个网络层增加名字，并通过下面这行代码打印出来

print(alexnet._modules['features']._modules.keys())

1. AlexNet

 

import os
import zipfile
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))
        
# unzip        
print(os.getcwd())
os.makedirs('data', exist_ok=True)

with zipfile.ZipFile('../input/dogs-vs-cats-redux-kernels-edition/train.zip') as train_zip:
    train_zip.extractall('data')
    
with zipfile.ZipFile('../input/dogs-vs-cats-redux-kernels-edition/test.zip') as test_zip:
    test_zip.extractall('data')


# show unzip dir
train_dir = './data/train'
test_dir = './data/test'

print('len:', len(os.listdir(train_dir)), len(os.listdir(test_dir)))
os.listdir(train_dir)[:5]
os.listdir(test_dir)[:5]



import numpy as np 
import pandas as pd 
import glob
import os
import torch
import matplotlib.pyplot as plt
from PIL import Image
from sklearn.model_selection import train_test_split
from torchvision import datasets, models, transforms
import torch.nn as nn
import torch.optim as optim


batch_size = 100

device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(device)

torch.manual_seed(1234)

if device =='cuda':
    torch.cuda.manual_seed_all(1234)
    
lr = 0.001


train_list = glob.glob(os.path.join(train_dir,'*.jpg'))
test_list = glob.glob(os.path.join(test_dir, '*.jpg'))

print('show data:', len(train_list), train_list[:3])
print('show data:', len(test_list), test_list[:3])


fig = plt.figure()
ax = fig.add_subplot(1,1,1)
img = Image.open(train_list[0])
plt.imshow(img)
plt.axis('off')
plt.show()
print(type(img))
img_np = np.asarray(img)
print(img_np.shape)



train_list, val_list = train_test_split(train_list, test_size=0.2)
print(len(train_list), train_list[:3])
print(len(val_list), val_list[:3])




train_transforms = transforms.Compose([
    transforms.Resize((224, 224)),
#     transforms.RandomCrop(224), 
    transforms.ToTensor(),
])

val_transforms = transforms.Compose([
    transforms.Resize((224, 224)),
#     transforms.RandomCrop(224), 
    transforms.ToTensor(),
])

test_transforms = transforms.Compose([
    transforms.Resize((224, 224)),
#     transforms.RandomCrop(224), 
    transforms.ToTensor(),
])


class dataset(torch.utils.data.Dataset):
    def __init__(self,file_list,now_transform):
        self.file_list = file_list # list of path
        self.transform = now_transform
    
    def __len__(self):
        self.filelength = len(self.file_list)
        return self.filelength
    
    def __getitem__(self,idx):
        img_path = self.file_list[idx]
        img = Image.open(img_path)
#         print(img.size)
        img_transformed = self.transform(img)
        
        # test 没有标签?
        label = img_path.split('/')[-1].split('.')[0]
        if label == 'dog':
            label=1
        elif label == 'cat':
            label=0
        else:
            assert False
            
        return img_transformed,label


train_data = dataset(train_list, train_transforms)
val_data = dataset(val_list, test_transforms)
# test_data = dataset(test_list, transform=test_transforms)

train_loader = torch.utils.data.DataLoader(dataset = train_data, batch_size=batch_size, shuffle=True )
val_loader = torch.utils.data.DataLoader(dataset = val_data, batch_size=batch_size, shuffle=True)
# test_loader = torch.utils.data.DataLoader(dataset = test_data, batch_size=batch_size, shuffle=True)

print(len(train_data), len(train_loader))
print(len(val_data), len(val_loader))
print(train_data, type(train_data))
t1, t2 = train_data[7]
print(t1, t2)
print(type(t1))
print(t1.shape)




class AlexNet(nn.Module):

    def __init__(self, num_classes = 2):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x



# model = CNN_STD().to(device)
model = AlexNet().to(device)
model.train()
print(model._modules.keys())
print(model._modules['features'][0])


optimizer = optim.Adam(params = model.parameters(),lr=lr)

loss_f = nn.CrossEntropyLoss()


epochs = 10

print('start epoch iter, please wait...')
for epoch in range(epochs):
    epoch_loss = 0
    epoch_accuracy = 0
    
    for data, label in train_loader:
        data = data.to(device)
        label = label.to(device)
        
        output = model(data)
        loss = loss_f(output, label)
        
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        acc = ((output.argmax(dim=1) == label).float().mean())
        epoch_accuracy += acc/len(train_loader)
        epoch_loss += loss/len(train_loader)
    
        
    print('Epoch : {}, train accuracy : {}, train loss : {}'.format(epoch+1, epoch_accuracy,epoch_loss))
    
    
    with torch.no_grad():
        epoch_val_accuracy=0
        epoch_val_loss =0
        for data, label in val_loader:
            data = data.to(device)
            label = label.to(device)
            
            val_output = model(data)
            val_loss = loss_f(val_output,label)
            
            
            acc = ((val_output.argmax(dim=1) == label).float().mean())
            epoch_val_accuracy += acc/ len(val_loader)
            epoch_val_loss += val_loss/ len(val_loader)
            
        print('Epoch : {}, val_accuracy : {}, val_loss : {}'.format(epoch+1, epoch_val_accuracy,epoch_val_loss))

 

注意, 猫狗大战训练效果不理想, 不知是数据太小, 还是代码错, 还是需要调超参