Question

当我使用Python在TensorFlow中使用神经网络进行预测时，出现以下错误：ValueError: Input 0 of layer dense is incompatible with the layer: expected axis -1 of input shape to have value 784 but received input with shape [None, 28]。

我正在尝试遵循Tensorflow网站上的教程来训练神经网络对服装进行分类。我编写了以下代码：

import tensorflow as tf
from tensorflow import keras
import matplotlib.pyplot as plt
import numpy as np
from skimage import color, io

print(tf.__version__)

data = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = data.load_data()

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
train_images = train_images / 255
test_images = test_images / 255


model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation="relu"),
    keras.layers.Dense(10, activation="softmax")
])

model.compile(
    optimizer="adam",
    loss="sparse_categorical_crossentropy",
    metrics=["accuracy"]
)

model.fit(train_images, train_labels, epochs=20)

print(type(test_images))
images = [test_images[0]]

predictions = model.predict(images)

print(class_names[np.argmax(predictions[0])])

任何帮助，TIA都很感谢。

Answer 1

为了社区的利益，来自评论部分。

通过将 model.predict(images) 更改为以下几行已解决了问题。

model.predict(np.expand_dims(test_images[0],0))

预测时，Tensorflow产生错误：预期输入形状的轴-1具有值784，但接收到形状为[None，28]的输入

1 个答案: