赛题来源自Google街景图像中的门牌号数据集(The Street View House Numbers Dataset, SVHN),并根据一定方式采样得到比赛数据集。
Field | Description |
---|---|
top | 左上角坐标Y |
height | 字符高度 |
left | 左上角坐标X |
width | 字符宽度 |
label | 字符编码 |
评价标准为准确率,选手提交结果与实际图片的编码进行对比,以编码整体识别准确率为评价指标,结果越大越好,具体计算公式如下:
s c o r e = 编 码 识 别 正 确 的 数 量 测 试 集 图 片 数 量 score = \frac{编码识别正确的数量}{测试集图片数量} score=测试集图片数量编码识别正确的数量
pytorch中所有的数据集均继承自torch.utils.data.Dataset,它们都需要实现了 _getitem_ 和 _len_ 两个接口,因此,实现一个数据集的核心也就是实现这两个接口。
首先看基于公开的CIFAR10数据集,我们有两种方式来读取,简单的一种是直接调用torchvision.datasets.CIFAR10,
from PIL import Image
import torch
import torchvision
from torch.utils.data.dataset import Dataset
import torchvision.transforms as transforms
# 读取训练集
train_data = torchvision.datasets.CIFAR10('../../../dataset',
train=True,
transform=None,
target_transform=None,
download=True)
"""
torchvision.datasets.CIFAR10(dataset_dir, train=True, transform=None, target_transform=None, download=False)
dataset_dir:存放数据集的路径。
train(bool,可选)–如果为True,则构建训练集,否则构建测试集。
transform:定义数据预处理,数据增强方案都是在这里指定。
target_transform:标注的预处理,分类任务不常用。
download:是否下载,若为True则从互联网下载,如果已经在dataset_dir下存在,就不会再次下载
"""
但一般情况下,如果非官方数据集,还是会对样本进行一定的数据增强,我们用transforms.Compose对数据做有先后顺序的变换:
# 读取训练集
custom_transform=transforms.transforms.Compose([
transforms.Resize((64, 64)), # 缩放到指定大小 64*64
transforms.ColorJitter(0.2, 0.2, 0.2), # 随机颜色变换
transforms.RandomRotation(5), # 随机旋转
transforms.Normalize([0.485,0.456,0.406], # 对图像像素进行归一化
[0.229,0.224,0.225])])
train_data=torchvision.datasets.CIFAR10('../../../dataset',
train=True,
transform=custom_transforms,
target_transform=None,
download=False)
数据集定义完成后,我们还需要进行数据加载。Pytorch提供DataLoader来完成对于数据集的加载,并且支持多进程并行读取。
# 读取数据集
train_data=torchvision.datasets.CIFAR10('../../../dataset', train=True,
transform=None,
target_transform=None,
download=True)
# 实现数据批量读取
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=2,
shuffle=True,
num_workers=4)
这里batch_size设置了批量大小,shuffle设置为True在装载过程中为随机乱序,num_workers>=1表示多进程读取数据,在Win下num_workers只能设置为0,否则会报错。而dataloader的语法为:
DataLoader(dataset, batch_size=1, shuffle=False, sampler=None, num_workers=0, collate_fn=default_collate, pin_memory=False, drop_last=False)
想要读取我们自己数据集中的数据,就需要写一个Dataset的子类来定义我们的数据集,并必须对 _init_、_getitem_ 和 _len_ 方法进行重载。下面我们看一下构建Dataset类的基本结构:
from torch.utils.data.dataset import Dataset
class MyDataset(Dataset): # 继承Dataset类
def __init__(self):
# 初始化图像文件路径或图像文件名列表等
pass
def __getitem__(self, index):
# 1.根据索引index从文件中读取一个数据(例如,使用numpy.fromfile,PIL.Image.open,cv2.imread)
# 2.预处理数据(例如torchvision.Transform)
# 3.返回数据对(例如图像和标签)
pass
def __len__(self):
return count # 返回数据量
"""
__init__() : 初始化模块,初始化该类的一些基本参数
__getitem__() : 接收一个index,这个index通常指的是一个list的index,这个list的每个元素就包含了图片数据的路径和标签信息,返回数据对(图像和标签)
__len__() : 返回所有数据的数量
"""
将其按照上面的思路补充完整,即能得到一个完整的读取图像的类,并通过该类读取特定图像数据。
import pandas as pd
import numpy as np
from PIL import Image
import torch
from torch.utils.data import Dataset
from torchvision import transforms
class MnistDataset(Dataset):
def __init__(self, image_path, image_label, transform=None):
super(MnistDataset, self).__init__()
self.image_path = image_path # 初始化图像路径列表
self.image_label = image_label # 初始化图像标签列表
self.transform = transform # 初始化数据增强方法
def __getitem__(self, index):
"""
获取对应index的图像,并视情况进行数据增强
"""
image = Image.open(self.image_path[index])
image = np.array(image)
label = float(self.image_label[index])
if self.transform is not None:
image = self.transform(image)
return image, torch.tensor(label)
def __len__(self):
return len(self.image_path)
def get_path_label(img_root, label_file_path):
"""
获取数字图像的路径和标签并返回对应列表
@para: img_root: 保存图像的根目录
@para:label_file_path: 保存图像标签数据的文件路径 .csv 或 .txt 分隔符为','
@return: 图像的路径列表和对应标签列表
"""
data = pd.read_csv(label_file_path, names=['img', 'label'])
data['img'] = data['img'].apply(lambda x: img_root + x)
return data['img'].tolist(), data['label'].tolist()
# 获取训练集路径列表和标签列表
train_data_root = './dataset/MNIST/mnist_data/train/'
train_label = './dataset/MNIST/mnist_data/train.txt'
train_img_list, train_label_list = get_path_label(train_data_root, train_label)
# 训练集dataset
train_dataset = MnistDataset(train_img_list,
train_label_list,
transform=transforms.Compose([transforms.ToTensor()]))
# 获取测试集路径列表和标签列表
test_data_root = './dataset/MNIST/mnist_data/test/'
test_label = './dataset/MNIST/mnist_data/test.txt'
test_img_list, test_label_list = get_path_label(test_data_root, test_label)
# 测试集sdataset
test_dataset = MnistDataset(test_img_list,
test_label_list,
transform=transforms.Compose([transforms.ToTensor()]))
首先安装一个新的虚拟环境针对当前场景,并安装所需要的包:
conda create -n py37_torch python=3.7
source activate py37_torch
conda install pytorch=1.3.1 torchvision cudatoolkit=10.0
# conda install pytorch-cpu
pip install tqdm pandas matplotlib opencv-python jupyter
class SVHNDataset(Dataset):
def __init__(self, img_path, img_label, transform=None):
self.img_path = img_path
self.img_label = img_label
if transform is not None:
self.transform = transform
else:
self.transform = None
def __getitem__(self, index):
img = Image.open(self.img_path[index]).convert('RGB')
if self.transform is not None:
img = self.transform(img)
lbl = np.array(self.img_label[index], dtype=np.int)
lbl = list(lbl) + (5 - len(lbl)) * [10]
return img, torch.from_numpy(np.array(lbl[:5]))
def __len__(self):
return len(self.img_path)
train_path = glob.glob('../../../dataset/tianchi_SVHN/train/*.png')
train_path.sort()
train_json = json.load(open('../../../dataset/tianchi_SVHN/train.json'))
train_label = [train_json[x]['label'] for x in train_json]
print(len(train_path), len(train_label))
train_loader = torch.utils.data.DataLoader(
SVHNDataset(train_path, train_label,
transforms.Compose([
transforms.Resize((64, 128)),
transforms.RandomCrop((60, 120)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=40,
shuffle=True,
num_workers=10,
)
val_path = glob.glob('../../../dataset/tianchi_SVHN/val/*.png')
val_path.sort()
val_json = json.load(open('../../../dataset/tianchi_SVHN/val.json'))
val_label = [val_json[x]['label'] for x in val_json]
print(len(val_path), len(val_label))
val_loader = torch.utils.data.DataLoader(
SVHNDataset(val_path, val_label,
transforms.Compose([
transforms.Resize((60, 120)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=40,
shuffle=False,
num_workers=10,
)
class SVHN_Model1(nn.Module):
def __init__(self):
super(SVHN_Model1, self).__init__()
model_conv = models.resnet18(pretrained=True)
model_conv.avgpool = nn.AdaptiveAvgPool2d(1)
model_conv = nn.Sequential(*list(model_conv.children())[:-1])
self.cnn = model_conv
self.fc1 = nn.Linear(512, 11)
self.fc2 = nn.Linear(512, 11)
self.fc3 = nn.Linear(512, 11)
self.fc4 = nn.Linear(512, 11)
self.fc5 = nn.Linear(512, 11)
def forward(self, img):
feat = self.cnn(img)
# print(feat.shape)
feat = feat.view(feat.shape[0], -1)
c1 = self.fc1(feat)
c2 = self.fc2(feat)
c3 = self.fc3(feat)
c4 = self.fc4(feat)
c5 = self.fc5(feat)
return c1, c2, c3, c4, c5
def train(train_loader, model, criterion, optimizer):
# 切换模型为训练模式
model.train()
train_loss = []
for i, (input, target) in enumerate(train_loader):
if use_cuda:
input = input.cuda()
target = target.cuda()
c0, c1, c2, c3, c4 = model(input)
loss = criterion(c0, target[:, 0]) + \
criterion(c1, target[:, 1]) + \
criterion(c2, target[:, 2]) + \
criterion(c3, target[:, 3]) + \
criterion(c4, target[:, 4])
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss.append(loss.item())
return np.mean(train_loss)
def validate(val_loader, model, criterion):
# 切换模型为预测模型
model.eval()
val_loss = []
# 不记录模型梯度信息
with torch.no_grad():
for i, (input, target) in enumerate(val_loader):
if use_cuda:
input = input.cuda()
target = target.cuda()
c0, c1, c2, c3, c4 = model(input)
loss = criterion(c0, target[:, 0]) + \
criterion(c1, target[:, 1]) + \
criterion(c2, target[:, 2]) + \
criterion(c3, target[:, 3]) + \
criterion(c4, target[:, 4])
val_loss.append(loss.item())
return np.mean(val_loss)
def predict(test_loader, model, tta=10):
model.eval()
test_pred_tta = None
# TTA 次数
for _ in range(tta):
test_pred = []
with torch.no_grad():
for i, (input, target) in enumerate(test_loader):
if use_cuda:
input = input.cuda()
c0, c1, c2, c3, c4 = model(input)
if use_cuda:
output = np.concatenate([
c0.data.cpu().numpy(),
c1.data.cpu().numpy(),
c2.data.cpu().numpy(),
c3.data.cpu().numpy(),
c4.data.cpu().numpy()], axis=1)
else:
output = np.concatenate([
c0.data.numpy(),
c1.data.numpy(),
c2.data.numpy(),
c3.data.numpy(),
c4.data.numpy()], axis=1)
test_pred.append(output)
test_pred = np.vstack(test_pred)
if test_pred_tta is None:
test_pred_tta = test_pred
else:
test_pred_tta += test_pred
return test_pred_tta
model = SVHN_Model1()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), 0.001)
use_cuda = True
if use_cuda:
model = model.cuda()
best_loss = 1000.0
for epoch in range(3):
train_loss = train(train_loader, model, criterion, optimizer)
val_loss = validate(val_loader, model, criterion)
val_label = [''.join(map(str, x)) for x in val_loader.dataset.img_label]
val_predict_label = predict(val_loader, model, 1)
val_predict_label = np.vstack([
val_predict_label[:, :11].argmax(1),
val_predict_label[:, 11:22].argmax(1),
val_predict_label[:, 22:33].argmax(1),
val_predict_label[:, 33:44].argmax(1),
val_predict_label[:, 44:55].argmax(1),
]).T
val_label_pred = []
for x in val_predict_label:
val_label_pred.append(''.join(map(str, x[x!=10])))
val_char_acc = np.mean(np.array(val_label_pred) == np.array(val_label))
print('Epoch: {0}, Train loss: {1} \t Val loss: {2} \t Val Acc: {3}'.format(epoch, train_loss, val_loss, val_char_acc))
# 记录下验证集精度
if val_loss < best_loss:
best_loss = val_loss
# print('Find better model in Epoch {0}, saving model.'.format(epoch))
torch.save(model.state_dict(), './model.pt')
test_path = glob.glob('../../../dataset/tianchi_SVHN/test_a/*.png')
test_path.sort()
test_label = [[1]] * len(test_path)
print(len(test_path), len(test_label))
test_loader = torch.utils.data.DataLoader(
SVHNDataset(test_path, test_label,
transforms.Compose([
transforms.Resize((70, 140)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=40,
shuffle=False,
num_workers=10,
)
# 加载保存的最优模型生成提交文件
model.load_state_dict(torch.load('model.pt'))
test_predict_label = predict(test_loader, model, 1)
print(test_predict_label.shape)
test_label = [''.join(map(str, x)) for x in test_loader.dataset.img_label]
test_predict_label = np.vstack([
test_predict_label[:, :11].argmax(1),
test_predict_label[:, 11:22].argmax(1),
test_predict_label[:, 22:33].argmax(1),
test_predict_label[:, 33:44].argmax(1),
test_predict_label[:, 44:55].argmax(1),
]).T
test_label_pred = []
for x in test_predict_label:
test_label_pred.append(''.join(map(str, x[x!=10])))
import pandas as pd
df_submit = pd.read_csv('../../../dataset/tianchi_SVHN/test_A_sample_submit.csv')
df_submit['file_code'] = test_label_pred
df_submit.to_csv('submit.csv', index=None)