将形状为（687，809）的目标数组传递为形状（None，25）的输出，同时将其用作损耗`binary_crossentropy

Question

我正在使用CNN并收到此错误。

r = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=50)

这是代码

以下是错误，请帮助我解决。

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-82-0b7c2e7fa2ce> in <module>()
----> 1 r = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=50)

6 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_utils.py in check_loss_and_target_compatibility(targets, loss_fns, output_shapes)
    808           raise ValueError('A target array with shape ' + str(y.shape) +
    809                            ' was passed for an output of shape ' + str(shape) +
--> 810                            ' while using as loss `' + loss_name + '`. '
    811                            'This loss expects targets to have the same shape '
    812                            'as the output.')

ValueError: A target array with shape (687, 809) was passed for an output of shape (None, 25) while using as loss `binary_crossentropy`. This loss expects targets to have the same shape as the output.

Answer 1

这类问题的主要原因是当数据尺寸与模型输出尺寸不匹配时。

要解决此问题，请检查是否正确创建了数据，并且数据是否与模型的最后（最终/输出）图层尺寸匹配。