如何将 MNIST 训练图像从 (60000, 28, 28) 重塑为

Question

我正在尝试使用 Keras 学习具有简单密集层的 MNIST 数据集。我希望我的图像大小为 16*16 而不是 28*28。我用了很多方法，但都不管用。这是简单的密集网络：import kerasimport numpy as npimport mnistfrom tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import Densefrom tensorflow.keras.utils import to_categoricaltrain_images = mnist.train_images()train_labels = mnist.train_labels()test_images = mnist.test_images()test_labels = mnist.test_labels()# Normalize the images.train_images = (train_images / 255) - 0.5test_images = (test_images / 255) - 0.5print(train_images.shape)print(test_images.shape)# Flatten the images.train_images = train_images.reshape((-1, 784))test_images = test_images.reshape((-1, 784))print(train_images.shape)print(test_images.shape)# Build the model.model = Sequential([    Dense(10, activation='softmax', input_shape=(784,)),])# Compile the model.model.compile(    optimizer='adam',    loss='categorical_crossentropy',    metrics=['accuracy'],)# Train the model.model.fit(    train_images,    to_categorical(train_labels),    epochs=5,    batch_size=32,)# Evaluate the model.model.evaluate(    test_images,    to_categorical(test_labels))# Save the model to disk.model.save_weights('model.h5')

Answer 1

尝试使用此方法一次调整所有图像的大小 -

#!pip install --upgrade tensorflow

#Assuming you are using tensorflow 2

import numpy as np

import tensorflow as tf

#creating dummy images

imgs = np.stack([np.eye(28), np.eye(28)])

print(imgs.shape)

#Output - (2,28,28) 2 images of 28*28

imgt = imgs.transpose(1,2,0)  #Bring the batch channel to the end (28,28,2)

imgs_resize = tf.image.resize(imgt, (16,16)).numpy() #apply resize (14,14,2)

imgs2 = imgs_resize.transpose(2,0,1) #bring the batch channel back to front (2,14,14)

print(imgs2.shape)

#Output - (2,16,16)