ValueError: `logits` and `labels` must have the same shape, received ((None, 10) vs (None, 11, 2, 2))

Question

输入：

x_train shape: (6000, 16, 16, 1)
x_test shape: (5000, 16, 16, 1)
y_test shape: (5000, 11, 2)
y_test shape: (5000, 16, 16, 1)
6000 train samples
5000 test samples

神经网络：-

batch_size = 128
num_classes = 10
epochs = 10
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),activation='relu',input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=tf.keras.optimizers.Adadelta(),metrics=['accuracy'])

错误：-

Epoch 1/10
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-47-628ddb8c3023> in <module>()
 ----> 1 hist = model.fit(x_train, 
 y_train,batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(x_test, 
  y_test))
  2 print("The model has successfully trained")
  3 model.save('mnist.h5')
  4 print("Saving the model as mnist.h5")

   1 frames
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py 
    in autograph_handler(*args, **kwargs)
    1127           except Exception as e:  # pylint:disable=broad-except
    1128             if hasattr(e, "ag_error_metadata"):

-> 1129 提高 e.ag_error_metadata.to_exception(e) 1130 其他： 1131 提高

    ValueError: in user code:

我尽力解释我的问题，如果有任何混淆，那么我的抱歉，让我知道，我会添加它。

Answer 1

如错误所述，虽然您的模型每个样本输出超过 10 classes 的预测，但您以某种不兼容的方式传递了“真实标签”，为什么您的标签是三维的？每个样本有一个 11x2x2 张量，而不是单热编码的 class 数字。

ValueError: `logits` and `labels` must have the same shape, received ((None, 10) vs (None, 11, 2, 2))

ValueError: `logits` and `labels` must have the same shape, received ((None, 10) vs (None, 11, 2, 2))

machine-learning

neural-network

pandas

deep-learning

conv-neural-network