kg cifar10笔记

13.13. 实战 Kaggle 比赛：图像分类 (CIFAR-10) — 动手学深度学习 2.0.0 documentation

没写完先存了

读文件部分

看看文件夹结构就可以懂了

import collections
import math
import os
import shutil
import pandas as pd
import torch
import torchvision
from torch import nn
from d2l import torch as d2l


#@save
d2l.DATA_HUB['cifar10_tiny'] = (d2l.DATA_URL + 'kaggle_cifar10_tiny.zip','2068874e4b9a9f0fb07ebe0ad2b29754449ccacd')

# 如果使用完整的Kaggle竞赛的数据集，设置demo为False
demo = True

if demo:#'..\\data\\kaggle_cifar10_tiny'
    data_dir = d2l.download_extract('cifar10_tiny')
else:
    data_dir = '../data/cifar-10/'

#@save
def read_csv_labels(fname):
    """读取fname来给标签字典返回一个文件名"""
    with open(fname, 'r') as f:
        # 跳过文件头行(列名)
        lines = f.readlines()[1:]
    tokens = [l.rstrip().split(',') for l in lines] # lstrip:用来去除开头字符、空白符
    return dict(((name, label) for name, label in tokens))

labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
#labels 的样子{'1': 'frog', '2': 'truck', '3': 'truck', '4': 'deer', ....
print('# 训练样本 :', len(labels))
print('# 类别 :', len(set(labels.values())))


#@save
def read_csv_labels(fname):
    """读取fname来给标签字典返回一个文件名"""
    with open(fname, 'r') as f:
        # 跳过文件头行(列名)
        lines = f.readlines()[1:]
    tokens = [l.rstrip().split(',') for l in lines]
    return dict(((name, label) for name, label in tokens))

labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
print('# 训练样本 :', len(labels))
print('# 类别 :', len(set(labels.values())))

#@save
def reorg_train_valid(data_dir, labels, valid_ratio):
    """将验证集从原始的训练集中拆分出来"""
    # 训练数据集中样本最少的类别中的样本数
    n = collections.Counter(labels.values()).most_common()[-1][1]
    # 验证集中每个类别的样本数
    n_valid_per_label = max(1, math.floor(n * valid_ratio))
    label_count = {}
    for train_file in os.listdir(os.path.join(data_dir, 'train')):
        label = labels[train_file.split('.')[0]]
        fname = os.path.join(data_dir, 'train', train_file)
        copyfile(fname, os.path.join(data_dir, 'train_valid_test',
                                     'train_valid', label))
        if label not in label_count or label_count[label] < n_valid_per_label:
            copyfile(fname, os.path.join(data_dir, 'train_valid_test',
                                         'valid', label))
            label_count[label] = label_count.get(label, 0) + 1
        else:
            copyfile(fname, os.path.join(data_dir, 'train_valid_test',
                                         'train', label))
    return n_valid_per_label


#@save
def reorg_test(data_dir):
    """在预测期间整理测试集，以方便读取"""
    for test_file in os.listdir(os.path.join(data_dir, 'test')):
        copyfile(os.path.join(data_dir, 'test', test_file),
                 os.path.join(data_dir, 'train_valid_test', 'test',
                              'unknown'))


def reorg_cifar10_data(data_dir, valid_ratio):
    labels = read_csv_labels(os.path.join(data_dir, 'trainLabels.csv'))
    reorg_train_valid(data_dir, labels, valid_ratio)
    reorg_test(data_dir)


batch_size = 32 if demo else 128
valid_ratio = 0.1
reorg_cifar10_data(data_dir, valid_ratio)