python keras binary_crossentropy に関して

Question

前提・実現したいこと

ValueError: logits and labels must have the same shape ((None, 1) vs (None, 2))

最終的に損出関数 binary_crossentropy を用いて出力１つを得たいのですが
なぜかこのエラーが出てしまいます。

この２つのデータのshapeは以下のような形です。
X.shape : (25923, 128, 128, 1)
Y.shape : (25923, 2)

発生している問題・エラーメッセージ

ValueError: in user code:

    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:756 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:152 __call__
        losses = call_fn(y_true, y_pred)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:256 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:1608 binary_crossentropy
        K.binary_crossentropy(y_true, y_pred, from_logits=from_logits), axis=-1)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/backend.py:4979 binary_crossentropy
        return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/nn_impl.py:174 sigmoid_cross_entropy_with_logits
        (logits.get_shape(), labels.get_shape()))

    ValueError: logits and labels must have the same shape ((None, 1) vs (None, 2))

該当のソースコード

#モデルを作成
model = Sequential()

#conv１層目
model.add(Conv2D(1, (3, 3), padding='same', activation = 'relu', input_shape=(128, 128, 1)))
model.add(AveragePooling2D(pool_size=(2, 2)))

#conv2層目
model.add(Conv2D(1, (3, 3), padding='same', activation = 'relu'))
model.add(AveragePooling2D(pool_size=(2, 2)))

#conv3層目
model.add(Conv2D(conv3, (3, 3), padding='same', activation = 'relu'))
model.add(AveragePooling2D(pool_size=(2, 2)))

#conv4層目
#model.add(Conv2D(30, (3, 3), padding='same', activation = 'relu'))
#model.add(MaxPooling2D(pool_size=(2, 2)))

#conv4層目
#model.add(Conv2D(1, (3, 3), padding='same', activation = 'relu'))
#model.add(MaxPooling2D(pool_size=(2, 2)))

 
model.add(Flatten())
model.add(Dense(1, activation = 'sigmoid'))
          

#モデルのコンパイル
#保存
model.compile(optimizer='SGD',
                           loss='binary_crossentropy',
                           metrics=['acc'])

#model.summary()

#予測
history = model.fit(X, Y, epochs = epochs)

#保存
model.save('model/D14_channel{0}.h5'.format(conv3), include_optimizer=False)

試したこと

なぜか最後のDence の出力2にすると正しく動きます。
よろしくお願いします。

Answer 1

最終的に損出関数 binary_crossentropy を用いて出力１つを得たい

と

Y.shape : (25923, 2)

は、矛盾してます

Y.shape : (25923, 1)
で、値が0か1となるようにします