Multithreading HDF5读取和拟合生成器多处理错误

我正在尝试对fit_生成器进行多处理

这些就是我面临的问题

trainable_model.fit_generator(load_random_cached_bottlenecks(BATCH_SIZE, label_map, training_addr_label_map, train_npy_dir, 'h5py', h5py_file_train),epochs = EPOCHS, steps_per_epoch=iterations_per_epoch_t, validation_data = load_random_cached_bottlenecks(BATCH_SIZE, label_map, validation_addr_label_map, val_npy_dir, 'h5py', h5py_file_val), validation_steps=iterations_per_epoch_v, workers = 1, callbacks = callback_list, use_multiprocessing = True, max_queue_size = 32)

导致问题的主要参数：

工作者

和

使用多处理

当

worker=1

时，

use\u multiprocessing=True/False

运行没有问题

如果

workers=5

，

使用\u multiprocessing=True

其抛出错误。奇怪的是它正在运行，但在一些随机的迭代中，我得到了如下错误

KeyError: 'Unable to open object (bad local heap signature)'

或

我用h5py来读取文件。我已经为此编写了自定义生成器

def load_random_cached_bottlenecks(batch_size, label_map,
 addr_label_map, dirs, comp_type = 'h5py', hdf5_file = None):
'''
Parameters
----------
batch_size: Number of bottlenecks to be loaded along with the labels
label_map: The dictionary that maps the class_names and the index
addr_label_map: The dictionary that maps addrs of bottlenecks and the labels
hdf5_file: This is the hdf5 file object with reading enabled.
Returns
-------
batch: (bottlenecks_train, bottlenecks_labels) a batch of them which is equal to batch_size
'''
while True:
    chosen_h5py = np.random.choice(dirs, size = batch_size)
    # chosen_h5py = [dirs[i] for i in batch_index]
    labels_for_chosen_h5py = [label_map[addr_label_map[i]] for i in chosen_h5py]
    h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
    h5py_onehot = to_categorical(labels_for_chosen_h5py, num_classes = LABEL_LENGTH)
    # print (h5py_data.shape)
    yield (h5py_data, h5py_onehot)

我已经提到了，但无法解决我的问题

Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.6/site-packages/keras/utils/data_utils.py", line 677, in _data_generator_task
generator_output = next(self._generator)
File "general_model.py", line 263, in load_random_cached_bottlenecks
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "/opt/anaconda3/lib/python3.6/site-packages/keras/utils/data_utils.py", line 677, in _data_generator_task
generator_output = next(self._generator)
File "general_model.py", line 263, in load_random_cached_bottlenecks
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "general_model.py", line 263, in <listcomp>
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "general_model.py", line 263, in <listcomp>
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "/opt/anaconda3/lib/python3.6/site-packages/h5py/_hl/group.py", line 177, in __getitem__
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5o.pyx", line 190, in h5py.h5o.open
File "/opt/anaconda3/lib/python3.6/site-packages/h5py/_hl/group.py", line 177, in __getitem__
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
KeyError: 'Unable to open object (wrong B-tree signature)'
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5o.pyx", line 190, in h5py.h5o.open
KeyError: 'Unable to open object (bad symbol table node signature)'
Traceback (most recent call last):
File "general_model.py", line 437, in <module>
train_with_bottlenecks(args, label_map, trainable_model, non_trainable_model, iterations_per_epoch_t, iterations_per_epoch_v)
File "general_model.py", line 326, in train_with_bottlenecks
validation_steps=iterations_per_epoch_v, workers = 4, callbacks = callback_list, use_multiprocessing = True, max_queue_size = 32)
File "/opt/anaconda3/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/opt/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 2194, in fit_generator
generator_output = next(output_generator)
File "/opt/anaconda3/lib/python3.6/site-packages/keras/utils/data_utils.py", line 793, in get
six.reraise(value.__class__, value, value.__traceback__)
File "/opt/anaconda3/lib/python3.6/site-packages/six.py", line 693, in reraise
raise value
   KeyError: 'Unable to open object (wrong B-tree signature)'

回溯（最近一次呼叫最后一次）：
文件“/opt/anaconda3/lib/python3.6/site packages/keras/utils/data_utils.py”，第677行，在数据生成器任务中
发电机输出=下一个（自发电机）
文件“general\u model.py”，第263行，在load\u random\u cached\u中
h5py_data=np.array（[hdf5_文件[i]表示所选_h5py中的i]）
文件“/opt/anaconda3/lib/python3.6/site packages/keras/utils/data_utils.py”，第677行，在数据生成器任务中
发电机输出=下一个（自发电机）
文件“general\u model.py”，第263行，在load\u random\u cached\u中
h5py_data=np.array（[hdf5_文件[i]表示所选_h5py中的i]）
文件“general_model.py”，第263行，在
h5py_data=np.array（[hdf5_文件[i]表示所选_h5py中的i]）
文件“h5py/_objects.pyx”，第54行，在h5py._objects.with_phil.wrapper中
文件“general_model.py”，第263行，在
h5py_data=np.array（[hdf5_文件[i]表示所选_h5py中的i]）
文件“h5py/_objects.pyx”，第54行，在h5py._objects.with_phil.wrapper中
文件“h5py/_objects.pyx”，第55行，在h5py._objects.with_phil.wrapper中
文件“h5py/_objects.pyx”，第55行，在h5py._objects.with_phil.wrapper中
文件“/opt/anaconda3/lib/python3.6/site packages/h5py/_-hl/group.py”，第177行，在__
oid=h5o.open（self.id，self.\u e（名称），lapl=self.\u lapl）
文件“h5py/_objects.pyx”，第54行，在h5py._objects.with_phil.wrapper中
文件“h5py/_objects.pyx”，第55行，在h5py._objects.with_phil.wrapper中
文件“h5py/h5o.pyx”，第190行，位于h5py.h5o.open中
文件“/opt/anaconda3/lib/python3.6/site packages/h5py/_-hl/group.py”，第177行，在__
oid=h5o.open（self.id，self.\u e（名称），lapl=self.\u lapl）
KeyError:“无法打开对象（错误的B树签名）”
文件“h5py/_objects.pyx”，第54行，在h5py._objects.with_phil.wrapper中
文件“h5py/_objects.pyx”，第55行，在h5py._objects.with_phil.wrapper中
文件“h5py/h5o.pyx”，第190行，位于h5py.h5o.open中
KeyError:“无法打开对象（错误符号表节点签名）”
回溯（最近一次呼叫最后一次）：
文件“general_model.py”，第437行，在
带瓶颈的训练（参数、标签映射、可训练模型、不可训练模型、每个历元的迭代次数、每个历元的迭代次数）
文件“general\u model.py”，第326行，在带有\u瓶颈的\u列中
验证步骤=迭代次数/历元，工人=4，回调=回调列表，使用多处理=真，最大队列大小=32）
文件“/opt/anaconda3/lib/python3.6/site packages/keras/legacy/interfaces.py”，第91行，在包装器中
返回函数（*args，**kwargs）
文件“/opt/anaconda3/lib/python3.6/site packages/keras/engine/training.py”，第2194行，在fit_生成器中
发电机输出=下一个（输出发电机）
get中的文件“/opt/anaconda3/lib/python3.6/site packages/keras/utils/data_utils.py”，第793行
六、重放（值、类、值、值、回溯）
文件“/opt/anaconda3/lib/python3.6/site packages/six.py”，第693行，重新登录
增值
KeyError:“无法打开对象（错误的B树签名）”

---

感谢您的帮助！提前谢谢

这本身不是一个解决方案，但这为我解决了这个问题

我遇到了一个类似的错误：

OSError:无法读取数据（错误的B树签名）

当尝试使用

fit_generator

时，当此生成器从

hdf5_文件中读取数据时，也在
anaconda3
虚拟环境中

在我的例子中，我创建了一个新的虚拟环境，并重新安装了它应该在其中工作的特定版本所需的依赖项，这样我的代码可以顺利运行
 我也有同样的问题。。。有人找到解决办法了吗？
Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.6/site-packages/keras/utils/data_utils.py", line 677, in _data_generator_task
generator_output = next(self._generator)
File "general_model.py", line 263, in load_random_cached_bottlenecks
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "/opt/anaconda3/lib/python3.6/site-packages/keras/utils/data_utils.py", line 677, in _data_generator_task
generator_output = next(self._generator)
File "general_model.py", line 263, in load_random_cached_bottlenecks
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "general_model.py", line 263, in <listcomp>
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "general_model.py", line 263, in <listcomp>
h5py_data = np.array([hdf5_file[i] for i in chosen_h5py])
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "/opt/anaconda3/lib/python3.6/site-packages/h5py/_hl/group.py", line 177, in __getitem__
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5o.pyx", line 190, in h5py.h5o.open
File "/opt/anaconda3/lib/python3.6/site-packages/h5py/_hl/group.py", line 177, in __getitem__
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
KeyError: 'Unable to open object (wrong B-tree signature)'
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5o.pyx", line 190, in h5py.h5o.open
KeyError: 'Unable to open object (bad symbol table node signature)'
Traceback (most recent call last):
File "general_model.py", line 437, in <module>
train_with_bottlenecks(args, label_map, trainable_model, non_trainable_model, iterations_per_epoch_t, iterations_per_epoch_v)
File "general_model.py", line 326, in train_with_bottlenecks
validation_steps=iterations_per_epoch_v, workers = 4, callbacks = callback_list, use_multiprocessing = True, max_queue_size = 32)
File "/opt/anaconda3/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/opt/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 2194, in fit_generator
generator_output = next(output_generator)
File "/opt/anaconda3/lib/python3.6/site-packages/keras/utils/data_utils.py", line 793, in get
six.reraise(value.__class__, value, value.__traceback__)
File "/opt/anaconda3/lib/python3.6/site-packages/six.py", line 693, in reraise
raise value
   KeyError: 'Unable to open object (wrong B-tree signature)'