如何修复此张量流代码中的类型错误？

Question

代码：

import tensorflow as tf
from tensorflow import keras


fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

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

model.compile(optimizer=tf.optimizers.Adam(),),
              loss = 'sparse_categorical_crossentropy')

model.fit(train_images,train_labels,epochs = 5)

test_loss, test_acc = model.evaluate (test_images, test_labels)

首先，我有'AttributeError：模块'tensorflow._api.v2.train'没有属性'AdamOptimizer'' 并将“optimizer=tf.train.AdamOptimizer()”更改为“tf.optimizers.Adam()”（有效），然后我遇到了另一个错误。（在[https://stackoverflow.com/questions/55318273/找到解决方案] tensorflow-api-v2-train-has-no-attribute-adamoptimizer] ）

错误：

line 25, in <module> test_loss, test_acc = model.evaluate(test_images, test_labels) ^^^^^^^^^^^^^^^^^^^ TypeError: cannot unpack non-iterable float object

这是 ChatGPT 给我的建议（也不起作用）：

import tensorflow as tf
from tensorflow import keras


fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

# Reshape the input data
train_images = train_images.reshape(train_images.shape[0], 28, 28, 1)

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

model.compile(optimizer=tf.optimizers.Adam(),
              loss='sparse_categorical_crossentropy')

model.fit(train_images, train_labels, epochs=5)

# Reshape the test data
test_images = test_images.reshape(test_images.shape[0], 28, 28, 1)

test_loss, test_acc = model.evaluate(test_images, test_labels)

还有我从《零到英雄》张量流 YT 视频中获取的所有代码

Answer 1

在编译中添加“准确性”指标：

model.compile(optimizer=tf.optimizers.Adam(),
              loss='sparse_categorical_crossentropy',
              metrics=['acc'])

没有它你只会得到损失值。