Python ValueError：检查目标时出错：预期密集_14有2维，但得到了具有形状的数组（144、11、1756）

我正在运行一个CNN，检查图像，但不分类。事实上，输出层是一个密集层，其参数为1d中标签中图像的大小

如下面代码所示，我使用的是model.fit_generator（）而不是model.fit，当开始训练模型时，出现以下错误：

“ValueError:检查目标时出错：预期密集_14有2个 维度，但获得了具有形状的数组（144、11、1756）”

这里附上了模型的摘要：

def generator(data_arr, batch_size = 12):

num = len(data_arr)

# Loop forever so the generator never terminates
while True: 

    #shuffle(data_arr)

    i = 0 

    for offset in range(0, num, batch_size):

        batch_samples = data_arr[offset:offset+batch_size]

        samples = []
        labels = []

        for i in range(0, offset+batch_size, 1): 

            for batch_sample in batch_samples:

                samples.append(data_arr[i][0])
                labels.append(data_arr[i][1])

            X_ = np.array(samples)
            Y_ = np.array(labels)

        i+= batch_size

        X_ = X_[:, :, :, newaxis]
        yield (X_, Y_)

# compile and train the model using the generator function
train_generator = generator(training_data, batch_size = 12)
validation_generator = generator(val_data, batch_size = 12)

run_opts = tf.RunOptions(report_tensor_allocations_upon_oom = True)

model = Sequential()

model.add(Conv2D(8, (3, 3), input_shape = (55,1756,1)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (3, 3)))

model.add(Conv2D(16, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (3, 3)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (3, 3)))

model.add(Activation('softmax'))
model.add(Flatten())  # this converts our 3D feature maps to 1D feature 
vectors
model.add(Dense(19316))

model.compile(loss = 'sparse_categorical_crossentropy',
          optimizer = 'adam',
          metrics = ['accuracy'],
          options = run_opts)

model.summary()

batch_size = 12
nb_epoch = 6

model.fit_generator(train_generator, 
                steps_per_epoch = len(training_data) ,
                epochs = nb_epoch,
                validation_data = validation_generator,
                validation_steps = len(val_data))

图层（类型）输出形状参数# conv2d_45（conv2d）（无，531754，8）80

---

激活57（激活）（无，53，1754，8）0

---

最大池2D_43（最大池（无，17584，8）0

---

conv2d_46（conv2d）（无、15、582、16）1168

---

激活（激活）（无、15、582、16）0

---

最大池2D_44（最大池（无、5194、16）0

---

conv2d_47（conv2d）（无、3、192、32）4640

---

激活59（激活）（无，3，192，32）0

---

最大池2D池45（最大池（无、1、64、32）0

---

激活(激活)(无,1,64,32)0

---

展平15（展平）（无，2048）0

---

稠密的（稠密的）（无，19316）39578484 总参数：39584372 可培训参数：39584372 不可训练参数：0

---

有什么建议吗？ 提前谢谢

代码：

def generator(data_arr, batch_size = 12):

num = len(data_arr)

# Loop forever so the generator never terminates
while True: 

    #shuffle(data_arr)

    i = 0 

    for offset in range(0, num, batch_size):

        batch_samples = data_arr[offset:offset+batch_size]

        samples = []
        labels = []

        for i in range(0, offset+batch_size, 1): 

            for batch_sample in batch_samples:

                samples.append(data_arr[i][0])
                labels.append(data_arr[i][1])

            X_ = np.array(samples)
            Y_ = np.array(labels)

        i+= batch_size

        X_ = X_[:, :, :, newaxis]
        yield (X_, Y_)

# compile and train the model using the generator function
train_generator = generator(training_data, batch_size = 12)
validation_generator = generator(val_data, batch_size = 12)

run_opts = tf.RunOptions(report_tensor_allocations_upon_oom = True)

model = Sequential()

model.add(Conv2D(8, (3, 3), input_shape = (55,1756,1)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (3, 3)))

model.add(Conv2D(16, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (3, 3)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size = (3, 3)))

model.add(Activation('softmax'))
model.add(Flatten())  # this converts our 3D feature maps to 1D feature 
vectors
model.add(Dense(19316))

model.compile(loss = 'sparse_categorical_crossentropy',
          optimizer = 'adam',
          metrics = ['accuracy'],
          options = run_opts)

model.summary()

batch_size = 12
nb_epoch = 6

model.fit_generator(train_generator, 
                steps_per_epoch = len(training_data) ,
                epochs = nb_epoch,
                validation_data = validation_generator,
                validation_steps = len(val_data))