Python 3.x 转换为与生成器类似的num样本属性错误：'；int'；对象没有属性'；形状'；

我已经使用Keras序列编写了一个自定义生成器，但在第一个纪元结束时，我得到了： 属性错误：自定义生成器对象没有属性“shape”

Ubuntu 18.04 Cuda 10 试过的Tensorflow 1.13和1.14 见本页： 我试着换衣服 从keras.utils导入序列 到 从tensorflow.python.keras.utils.data\u utils导入序列 但是没有运气

class CustomGenerator(Sequence):

def __init__(self, ....):
    ...
    # Preallocate memory
    if mode == 'train' and self.crop_shape:
        self.X = np.zeros((batch_size, crop_shape[0], crop_shape[1], 4), dtype='float32')
        # edge
        # self.X2 = np.zeros((batch_size, crop_shape[1], crop_shape[0], 3), dtype='float32')

        self.Y1 = np.zeros((batch_size, crop_shape[0] // 4, crop_shape[1] // 4, self.n_classes), dtype='float32')

def on_epoch_end(self):
    # Shuffle dataset for next epoch
    c = list(zip(self.image_path_list, self.label_path_list, self.edge_path_list))
    random.shuffle(c)
    self.image_path_list, self.label_path_list, self.edge_path_list = zip(*c)

    # Fix memory leak (tensorflow.python.keras bug)
    gc.collect()


def __getitem__(self, index):
    for n, (image_path, label_path,edge_path) in enumerate(
            zip(self.image_path_list[index * self.batch_size:(index + 1) * self.batch_size],
                self.label_path_list[index * self.batch_size:(index + 1) * self.batch_size],
                self.edge_path_list[index * self.batch_size:(index + 1) * self.batch_size])):

        image = cv2.imread(image_path, 1)
        label = cv2.imread(label_path, 0)

        edge = cv2.imread(edge_path, 0)

        ....

        self.X[n] = image
        self.Y1[n] = to_categorical(cv2.resize(label, (label.shape[1] // 4, label.shape[0] // 4)),
                                    self.n_classes).reshape((label.shape[0] // 4, label.shape[1] // 4, -1))
        self.Y2[n] = to_categorical(cv2.resize(label, (label.shape[1] // 8, label.shape[0] // 8)),
                                    self.n_classes).reshape((label.shape[0] // 8, label.shape[1] // 8, -1))
        self.Y3[n] = to_categorical(cv2.resize(label, (label.shape[1] // 16, label.shape[0] // 16)),
                                    self.n_classes).reshape((label.shape[0] // 16, label.shape[1] // 16, -1))

    return self.X, [self.Y1, self.Y2, self.Y3]

def __len__(self):
    return math.floor(len(self.image_path_list) / self.batch_size)

def random_crop(image, edge, label, random_crop_size=(800, 1600)):
    ....
    return image, label

错误是：

742/743 [============================>.] - ETA: 0s - loss: 1.8465 - conv6_cls_loss: 1.1261 - sub24_out_loss: 1.2478 - sub4_out_loss: 1.3827 - conv6_cls_categorical_accuracy: 0.6705 - sub24_out_categorical_accuracy: 0.6250 - sub4_out_categorical_accuracy: 0.5963Traceback (most recent call last):
  File "/home/user/Desktop/Keras-ICNet/train1.py", line 75, in <module>
    use_multiprocessing=True, shuffle=True, max_queue_size=10, initial_epoch=opt.epoch)
  File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1433, in fit_generator
    steps_name='steps_per_epoch')
  File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 322, in model_iteration
    steps_name='validation_steps')
  File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 144, in model_iteration
    shuffle=shuffle)
  File "/home/user/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 480, in convert_to_generator_like
    num_samples = int(nest.flatten(data)[0].shape[0])
AttributeError: 'int' object has no attribute 'shape'

742/743[=========================>-预计到达时间：0s-损失：1.8465-conv6-cls-loss:1.1261-sub24-out-loss:1.2478-sub4-out-loss:1.3827-conv6-cls-out分类准确率：0.6705-sub24-out分类准确率：0.6250-sub4-out分类准确率：0.5963（最近一次呼叫回溯）：
文件“/home/user/Desktop/Keras ICNet/train1.py”，第75行，在
使用多处理=真，随机播放=真，最大队列大小=10，初始\u epoch=opt.epoch）
文件“/home/user/.local/lib/python3.6/site packages/tensorflow/python/keras/engine/training.py”，第1433行，在fit_生成器中
步骤（名称=“每个时代的步骤”）
文件“/home/user/.local/lib/python3.6/site packages/tensorflow/python/keras/engine/training\u generator.py”，第322行，在模型迭代中
步骤（name='validation'）
文件“/home/user/.local/lib/python3.6/site packages/tensorflow/python/keras/engine/training\u generator.py”，第144行，在模型迭代中
洗牌
文件“/home/user/.local/lib/python3.6/site packages/tensorflow/python/keras/engine/training\u generator.py”，第480行，类似convert\u to\u generator
num_samples=int（nest.flatte（数据）[0].shape[0]）
AttributeError:“int”对象没有属性“shape”

查看堆栈跟踪

num_samples = int(nest.flatten(data)[0].shape[0])
AttributeError: 'int' object has no attribute 'shape'

---

数据

实际上是指在

fit\u生成器

中传递的

validation\u数据

参数。这应该是一个生成器或元组。我猜这是作为数组传递的，其结果是

nest.flatte（data）[0]

返回

int

，因此返回错误。

查看堆栈跟踪

num_samples = int(nest.flatten(data)[0].shape[0])
AttributeError: 'int' object has no attribute 'shape'

---

数据

实际上是指在

fit\u生成器

中传递的

validation\u数据

参数。这应该是一个生成器或元组。我猜这是作为数组传递的，其结果是

nest.flatte（data）[0]

返回

int

，因此返回错误。

您如何知道它引用的是

验证\u data

？火车和验证数据都是从

\uuu getitem\uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu（self，index）

返回self.X、[self.Y1，self.Y2，self.Y3]如果传递给fit生成器的验证数据参数是生成器，则不会发生此。如果您可以将培训代码也包括在问题中，将更容易确定问题的原因。问题解决后，参数置换您如何知道它指的是

验证\u数据

？火车和验证数据都是从

\uuu getitem\uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu（self，index）

返回self.X、[self.Y1，self.Y2，self.Y3]如果传递给fit生成器的验证数据参数是生成器，则不会发生此。如果您可以将培训代码也包括在问题中，则更容易确定问题的原因。问题解决后，参数置换能否请您更新问题，使其也包括如何调用fit_生成器方法？能否请您更新问题，使其也包括如何调用fit_生成器方法？