CNN实战

目录

• 1.VGG模型使用练习
• 2.AI研习社猫狗大战赛题

1.VGG模型使用练习

数据处理

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)

torchvision已经预先实现了常用的Dataset，包括前面使用过的CIFAR-10，以及ImageNet、COCO、MNIST、LSUN等数据集，可通过诸如torchvision.datasets.CIFAR10来调用。ImageFolder假设所有的文件按文件夹保存，每个文件夹下存储同一个类别的图片，文件夹名为类名，其构造函数如下：ImageFolder(root, transform=None, target_transform=None, loader=default_loader)。root：在root指定的路径下寻找图片。transform：对PIL Image进行的转换操作，transform的输入是使用loader读取图片的返回对象。target_transform：对label的转换。loader：给定路径后如何读取图片，默认读取为RGB格式的PIL Image对象

模型

model_vgg = models.vgg16(pretrained=True)
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)

训练

criterion = nn.NLLLoss()
lr = 0.001
optimizer_vgg = torch.optim.SGD(model_vgg_new.classifier[6].parameters(),lr = lr)
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))
train_model(model_vgg_new,loader_train,size=dset_sizes['train'], epochs=1, 
            optimizer=optimizer_vgg)

2.AI研习社猫狗大战赛题

将数据分为两个文件夹

import os
import shutil
path_img = r'cat_dog/train'
path2 = r'cat_dog/train/cat'
path3 = r'cat_dog/train/dog'
os.makedirs(path2)
os.makedirs(path3)
path2 += '/'
path3 += '/'
for i in range(10000):
    shutil.move(path_img + '/cat_' + str(i) + ".jpg", path2 +str(i) + ".jpg")
for i in range(10000):
    shutil.move(path_img + '/dog_' + str(i) + ".jpg", path3 +str(i) + ".jpg")

模型

model_vgg = models.vgg16(pretrained=True)
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)

训练代码如上。