%cd ~!mkdir dataset !mkdir dataset/train!mkdir dataset/testimport cv2import randomimport numpy as npfrom tqdm import tqdmfrom paddle.vision.datasets import MNIST# 加载数据集mnist_train = MNIST(mode='train', backend='cv2')mnist_test = MNIST(mode='test', backend='cv2')# 数据集预处理datas_train = {}for i in range(len(mnist_train)): sample = mnist_train[i] x, y = sample[0], sample[1] _sum = np.sum(x, axis=0) _where = np.where(_sum > 0) x = 255 - x[:, _where[0][0]: _where[0][-1]+1] if str(y[0]) in datas_train: datas_train[str(y[0])].append(x) else: datas_train[str(y[0])] = [x]datas_test = {}for i in range(len(mnist_test)): sample = mnist_test[i] x, y = sample[0], sample[1] _sum = np.sum(x, axis=0) _where = np.where(_sum > 0) x = 255 - x[:, _where[0][0]: _where[0][-1]+1] if str(y[0]) in datas_test: datas_test[str(y[0])].append(x) else: datas_test[str(y[0])] = [x]# 图片拼接采样datas_train_list = []for num in tqdm(range(0, 999)): for _ in range(1000): imgs = [255 - np.zeros((28, np.random.randint(10)))] for word in str(num): index = np.random.randint(0, len(datas_train[word])) imgs.append(datas_train[word][index]) imgs.append(255 - np.zeros((28, np.random.randint(10)))) img = np.concatenate(imgs, 1) cv2.imwrite('dataset/train/%03d_%04d.jpg' % (num, _), img) datas_train_list.append('train/%03d_%04d.jpgt%dn' % (num, _, num))datas_test_list = []for num in tqdm(range(0, 999)): for _ in range(50): imgs = [255 - np.zeros((28, np.random.randint(10)))] for word in str(num): index = np.random.randint(0, len(datas_test[word])) imgs.append(datas_test[word][index]) imgs.append(255 - np.zeros((28, np.random.randint(10)))) img = np.concatenate(imgs, 1) cv2.imwrite('dataset/test/%03d_%04d.jpg' % (num, _), img) datas_test_list.append('test/%03d_%04d.jpgt%dn' % (num, _, num))# 数据列表生成with open('dataset/train.txt', 'w') as f: for line in datas_train_list: f.write(line)with open('dataset/test.txt', 'w') as f: for line in datas_test_list: f.write(line)登录后复制 ? ?

数据样例展示