使用 Keras 训练数据时遇到问题

Question

美好的一天，我正在与 Google colab 一起训练模型，当我尝试运行这段代码时

history_1 = model_1.fit(x_train, y_train, epochs=1000, batch_size=16, validation_data=(x_validate, y_validate))

我得到错误：

ValueError                                Traceback (most recent call last)
<ipython-input-3-bd00c937585f> in <module>()
----> 1 history_1 = model_1.fit(x_train, y_train, epochs=1000, batch_size=16, validation_data=(x_validate, y_validate))

3 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training_utils.py in check_loss_and_target_compatibility(targets, loss_fns, output_shapes)
    683           raise ValueError('A target array with shape ' + str(y.shape) +
    684                            ' was passed for an output of shape ' + str(shape) +
--> 685                            ' while using as loss `' + loss_name + '`. '
    686                            'This loss expects targets to have the same shape '
    687                            'as the output.')

ValueError: A target array with shape (600, 1) was passed for an output of shape (None, 16) while using as loss `mean_squared_error`. This loss expects targets to have the same shape as the output.

我不确定我的输入有什么问题，我遵循 TinyML 书中的示例，有人可以帮助澄清如何解决这个问题吗？

Answer 1

尝试使用 SparseCategoricalCrossentropy 而不是 CategoricalCrossentropy。看起来您的基本事实标签很稀疏。