尝试进行一个单标签分类问题，其中num_classes = 73
这是我简化的Keras模型：
num_classes = 73batch_size = 4train_data_list = [training_file_names list here..]validation_data_list = [ validation_file_names list here..]training_generator = DataGenerator(train_data_list, batch_size, num_classes)validation_generator = DataGenerator(validation_data_list, batch_size, num_classes)model = Sequential()model.add(Conv1D(32, 3, strides=1, input_shape=(15,120), activation="relu"))model.add(Conv1D(16, 3, strides=1, activation="relu"))model.add(Flatten())model.add(Dense(n_classes, activation='softmax'))sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)model.compile(loss="categorical_crossentropy",optimizer=sgd,metrics=['accuracy'])model.fit_generator(generator=training_generator, epochs=100, validation_data=validation_generator)这是我的DataGenerator的__get_item__方法：
def __get_item__(self): X = np.zeros((self.batch_size,15,120)) y = np.zeros((self.batch_size, 1 ,self.n_classes)) for i in range(self.batch_size): X_row = some_method_that_gives_X_of_15x20_dim() target = some_method_that_gives_target() one_hot = keras.utils.to_categorical(target, num_classes=self.n_classes) X[i] = X_row y[i] = one_hot return X, y由于我的X值的维度(batch_size, 15, 120)正确返回，这里就不展示了。我的问题在于返回的y值。
这个生成器方法返回的y的形状为(batch_size, 1, 73)，作为73个类的独热编码标签，我认为这是正确的返回形状。
然而，Keras在最后一层给出了以下错误：
ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (4, 1, 73)
由于批量大小为4，我认为目标批量也应该是三维的(4,1,73)。那么为什么Keras期望最后一层是二维的呢？
回答：
你的模型摘要显示，输出层应该只有2个维度，(None, 73)
_________________________________________________________________Layer (type) Output Shape Param # =================================================================conv1d_7 (Conv1D) (None, 13, 32) 11552 _________________________________________________________________conv1d_8 (Conv1D) (None, 11, 16) 1552 _________________________________________________________________flatten_5 (Flatten) (None, 176) 0 _________________________________________________________________dense_4 (Dense) (None, 73) 12921 =================================================================Total params: 26,025Trainable params: 26,025Non-trainable params: 0_________________________________________________________________由于你的目标的维度是(batch_size, 1, 73)，你只需将其更改为(batch_size, 73)，这样你的模型就可以运行了
