我尝试在keras版本的mrcnn的shapes示例中运行train代码，这里是github链接：https://github.com/matterport/Mask_RCNN/blob/master/samples/shapes/train_shapes.ipynb我尝试了更大的内存并减少每个历元的图像数量，但没有成功，所以这不是内存的问题。这是代码
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE,
epochs=1,
layers='heads')
这是错误：
OSError Traceback (most recent call last)
<ipython-input-15-83fb3ae74319> in <module>()
6 learning_rate=config.LEARNING_RATE,
7 epochs=1,
----> 8 layers='heads')
~/RCNN/MRCNN/Mask_RCNN/mrcnn/model.py in train(self, train_dataset, val_dataset, learning_rate, epochs, layers, augmentation)
2350 max_queue_size=100,
2351 workers=workers,
-> 2352 use_multiprocessing=True,
2353 )
2354 self.epoch = max(self.epoch, epochs)
~/.conda/envs/21/lib/python3.6/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name +
90 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/.conda/envs/21/lib/python3.6/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1424 use_multiprocessing=use_multiprocessing,
1425 shuffle=shuffle,
-> 1426 initial_epoch=initial_epoch)
1427
1428 @interfaces.legacy_generator_methods_support
~/.conda/envs/21/lib/python3.6/site-packages/keras/engine/training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
135 use_multiprocessing=use_multiprocessing,
136 wait_time=wait_time)
--> 137 enqueuer.start(workers=workers, max_queue_size=max_queue_size)
138 output_generator = enqueuer.get()
139 else:
~/.conda/envs/21/lib/python3.6/site-packages/keras/utils/data_utils.py in start(self, workers, max_queue_size)
724 thread = threading.Thread(target=self._data_generator_task)
725 self._threads.append(thread)
--> 726 thread.start()
727 except:
728 self.stop()
~/.conda/envs/21/lib/python3.6/multiprocessing/process.py in start(self)
103 'daemonic processes are not allowed to have children'
104 _cleanup()
--> 105 self._popen = self._Popen(self)
106 self._sentinel = self._popen.sentinel
107 # Avoid a refcycle if the target function holds an indirect
~/.conda/envs/21/lib/python3.6/multiprocessing/context.py in _Popen(process_obj)
221 @staticmethod
222 def _Popen(process_obj):
--> 223 return _default_context.get_context().Process._Popen(process_obj)
224
225 class DefaultContext(BaseContext):
~/.conda/envs/21/lib/python3.6/multiprocessing/context.py in _Popen(process_obj)
275 def _Popen(process_obj):
276 from .popen_fork import Popen
--> 277 return Popen(process_obj)
278
279 class SpawnProcess(process.BaseProcess):
~/.conda/envs/21/lib/python3.6/multiprocessing/popen_fork.py in __init__(self, process_obj)
17 util._flush_std_streams()
18 self.returncode = None
---> 19 self._launch(process_obj)
20
21 def duplicate_for_child(self, fd):
~/.conda/envs/21/lib/python3.6/multiprocessing/popen_fork.py in _launch(self, process_obj)
64 code = 1
65 parent_r, child_w = os.pipe()
---> 66 self.pid = os.fork()
67 if self.pid == 0:
68 try:
OSError: [Errno 12] Cannot allocate memory
我将use_multiprocessing更改为False仍然不起作用。有人知道为什么会发生这个错误吗？谢谢
堆栈跟踪来自启用了多处理的运行，因此它并不能真正提供其他问题的信息。
减少max_queue_size可能有效。GPU内存不足时，通常建议减少批处理大小。但你的普通RAM快用完了。