深度学习TOP方案解析系列视频课
查看数据集大小
if __name__ == '__main__':
TRAIN_DF = 'data/train.csv'
SUBMIT_DF = 'data/sample_submission.csv'
tagged = dict([(p, w) for _, p, w in pd.read_csv(TRAIN_DF).to_records()])
submit = [p for _, p, _ in pd.read_csv(SUBMIT_DF).to_records()]
join = list(tagged.keys()) + submit # 训练集和测试集所有图片名字的总和 print('给定的训练集大小：{}'.format(len(tagged)))
print('给定的测试集大小：{}'.format(len(submit)))
print('全部图片数量：{}'.format(len(join)))
print('训练集前5个样本：{}'.format(list(tagged.items())[:5]))
print('测试集前5个样本：{}'.format(submit[:5]))
