如何将 MNIST 训练图像从 (60000, 28, 28) 重塑为 (60000, 16, 16)？答案

【问题标题】：how to reshape the MNIST train images from (60000, 28, 28) to (60000, 16, 16)?如何将 MNIST 训练图像从 (60000, 28, 28) 重塑为 (60000, 16, 16)？
【发布时间】：2020-11-29 05:21:33
【问题描述】：

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。我使用了很多方法，但它们不起作用。这是简单的密集网络：

import keras
import numpy as np
import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical

train_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) - 0.5
test_images = (test_images / 255) - 0.5
print(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')

【问题讨论】：

标签： python keras reshape mnist

【解决方案1】：

试试这个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)

【讨论】：