如何正确设置Conv2D参数？

Question

我正在尝试在MNIST数据集上构建CNN模型，但是出现错误，我无法解决。这是我的代码

import tensorflow as tf
from tensorflow.keras.datasets import mnist
from keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import Dense, Flatten, Conv2D
from numpy import expand_dims
(x_train, y_train), (x_test, y_test) = mnist.load_data() 
x_train = expand_dims(x_train, 3)
x_test = expand_dims(x_test, 3)
y_train = to_categorical(y_train) 
y_test = to_categorical(y_test)
model = Sequential()
model.add(Conv2D(64, kernel_size=3, activation="relu", input_shape=(28, 28, 1)))
model.add(Conv2D(64, kernel_size=3, activation="relu"))
model.add(Flatten())
model.add(Dense(10, activation="softmax"))
model.compile(optimizer="adam", loss="categorical_crossentropy", metrics=["accuracy"])
model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=3)
model.save("model")
new_model = tf.keras.models.load_model("model")
predictions = new_model.predict([x_test])
print(predictions[10])

我收到此错误

TypeError: Value passed to parameter 'input' has DataType uint8 not in list of allowed values: float16, bfloat16, float32, float64

有帮助吗？

Answer 1

您收到此错误，是因为您的输入是uint8类型，而网络具有浮点值。您只需要将输入转换为浮点数据类型即可。在这里，将您的数据部分更改为：

import numpy as np
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = expand_dims(x_train, -1)
x_test = expand_dims(x_test, -1)
x_train = x_train.astype(np.float32)
x_test = x_test.astype(np.float32)

[很奇怪，我没有收到您的错误，但我应该知道，这就是解决方案。