tf.data.Dataset.from_tensor_slices()

tf.data.Dataset.from_tensor_slices(tensors, name=None)

该函数的作用是接收tensor，对tensor的第一维度进行切分，并返回一个表示该tensor的切片数据集

# Slicing a 1D tensor produces scalar tensor elements.
import tensorflow as tf

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
print(dataset)
print(list(dataset.as_numpy_iterator()))

 

import tensorflow as tf

# Slicing a 2D tensor produces 1D tensor elements.
dataset = tf.data.Dataset.from_tensor_slices([[1, 2], [3, 4]])
print(dataset)
print(list(dataset.as_numpy_iterator()))

import tensorflow as tf

# Dictionary structure is also preserved.
dataset = tf.data.Dataset.from_tensor_slices({"a": [1, 2], "b": [3, 4]})
print(dataset)
print(list(dataset.as_numpy_iterator()))

import tensorflow as tf
import numpy as np
x = np.random.uniform(size=(5, 2))
#print(x)
dataset = tf.data.Dataset.from_tensor_slices(x)
for ele in dataset:
	print(ele)

import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
def load_dataset():
    # Step0 准备数据集, 可以是自己动手丰衣足食, 也可以从 tf.keras.datasets 加载需要的数据集(获取到的是numpy数据)
    # 这里以 mnist 为例
    (x, y), (x_test, y_test) = keras.datasets.mnist.load_data()

    # Step1 使用 tf.data.Dataset.from_tensor_slices 进行加载
    db_train = tf.data.Dataset.from_tensor_slices((x,y))
    db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))

    # Step2 打乱数据
    db_train.shuffle(1000)
    db_test.shuffle(1000)

    # Step3 预处理 (预处理函数在下面)
    db_train.map(preprocess)
    db_test.map(preprocess)

    # Step4 设置 batch size 一次喂入64个数据
    db_train.batch(64)
    db_test.batch(64)

    # Step5 设置迭代次数(迭代2次) test数据集不需要emmm
    db_train.repeat(2)

    return db_train, db_test


def preprocess(labels, images):
    '''
    最简单的预处理函数:
        转numpy为Tensor、分类问题需要处理label为one_hot编码、处理训练数据
    '''
    # 把numpy数据转为Tensor
    labels = tf.cast(labels, dtype=tf.int32)
    # labels 转为one_hot编码
    labels = tf.one_hot(labels, depth=10)
    # 顺手归一化
    images = tf.cast(images, dtype=tf.float32) / 255
    return labels, images

train,test=load_dataset()

for image in train:
    print(type(image))
    image=np.array(image)
    # print(image)
    print(image[0].shape)
    plt.axis('off')
    plt.imshow(image[0],cmap='gray')
    plt.show()
    break

 

import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
def load_dataset():
    # Step0 准备数据集, 可以是自己动手丰衣足食, 也可以从 tf.keras.datasets 加载需要的数据集(获取到的是numpy数据)
    # 这里以 mnist 为例
    (x, y), (x_test, y_test) = keras.datasets.mnist.load_data()

    # Step1 使用 tf.data.Dataset.from_tensor_slices 进行加载
    db_train = tf.data.Dataset.from_tensor_slices((x,y))
    db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))

    # Step2 打乱数据
    db_train.shuffle(1000)
    db_test.shuffle(1000)

    # Step3 预处理 (预处理函数在下面)
    db_train.map(preprocess)
    db_test.map(preprocess)

    # Step4 设置 batch size 一次喂入64个数据
    db_train.batch(64)
    db_test.batch(64)

    # Step5 设置迭代次数(迭代2次) test数据集不需要emmm
    db_train.repeat(2)

    return db_train, db_test


def preprocess(labels, images):
    '''
    最简单的预处理函数:
        转numpy为Tensor、分类问题需要处理label为one_hot编码、处理训练数据
    '''
    # 把numpy数据转为Tensor
    labels = tf.cast(labels, dtype=tf.int32)
    # labels 转为one_hot编码
    labels = tf.one_hot(labels, depth=10)
    # 顺手归一化
    images = tf.cast(images, dtype=tf.float32) / 255
    return labels, images

train,test=load_dataset()

for image in train.as_numpy_iterator():
    print(image[0])
    image=np.array(image[0])
    print(image.shape)
    plt.imshow(image,cmap='gray')
    plt.show()
    break

 

 使用tf.data.Dataset.from_tensor_slices五步加载数据集_rainweic的博客-CSDN博客