零基础入门CV之街道字符识别-Task02数据读取与数据扩增

数据读取

赛方为方便进行数据读取，已经给出JSON中标签的读取方式：

import json
train_json = json.load(open('../input/train.json'))

# 数据标注处理
def parse_json(d):
    arr = np.array([
        d['top'], d['height'], d['left'],  d['width'], d['label']
    ])
    arr = arr.astype(int)
    return arr

img = cv2.imread('../input/train/000000.png')
arr = parse_json(train_json['000000.png'])

plt.figure(figsize=(10, 10))
plt.subplot(1, arr.shape[1]+1, 1)
plt.imshow(img)
plt.xticks([]); plt.yticks([])

for idx in range(arr.shape[1]):
    plt.subplot(1, arr.shape[1]+1, idx+2)
    plt.imshow(img[arr[0, idx]:arr[0, idx]+arr[1, idx],arr[2, idx]:arr[2, idx]+arr[3, idx]])
    plt.title(arr[4, idx])
    plt.xticks([]); plt.yticks([])

数据扩增

在深度学习中数据扩增方法非常重要，数据扩增可以增加训练集的样本，同时也可以有效缓解模型过拟合的情况，也可以给模型带来的更强的泛化能力

代码：

import os, sys, glob, shutil, json
import cv2

from PIL import Image
import numpy as np

import torch
from torch.utils.data.dataset import Dataset
import torchvision.transforms as transforms

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)
        
        # 原始SVHN中类别10为数字0
        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('../input/train/*.png')
train_path.sort()
train_json = json.load(open('../input/train.json'))
train_label = [train_json[x]['label'] for x in train_json]

train_loader = torch.utils.data.DataLoader(
        SVHNDataset(train_path, train_label,
                   transforms.Compose([
                       transforms.Resize((64, 128)),
                       transforms.ColorJitter(0.3, 0.3, 0.2),
                       transforms.RandomRotation(5),
                       transforms.ToTensor(),
                       transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
            ])), 
    batch_size=10, # 每批样本个数
    shuffle=False, # 是否打乱顺序
    num_workers=10, # 读取的线程个数
)

for data in train_loader:
    break