重新启动后，在不接触任何其他内容的情况下，我打开 Jupyter Notebook 并尝试运行使 GPU 开始训练的单元。
但在我的终端中，我收到此消息，在笔记本中，我收到下面的长错误。 (我使用的是 Ubuntu 16.04、带有 Tensorflow 后端的 Keras)。
87] Found device 1 with properties:
name: GeForce GTX 1080 Ti
major: 6 minor: 1 memoryClockRate (GHz) 1.582
pciBusID 0000:25:00.0
Total memory: 10.91GiB
Free memory: 396.44MiB
此处笔记本的代码 https://github.com/fastai/courses/blob/master/deeplearning1/nbs/lesson1.ipynb
在单元格 [5] 中，我将批量大小降低到 10，然后尝试了 5。我还设置了 no_of_epochs=5。除了重新启动之外，我还尝试寻找任何命令来让系统删除 GPU 可能正在使用的任何进程，但它似乎没有使用任何进程。
单元格 [7] 是运行时给出以下所有错误的单元格。
这是尝试利用 GPU 的单元 [7] 下的完整错误。
---------------------------------------------------------------------------
ResourceExhaustedError Traceback (most recent call last)
<ipython-input-7-2b6861506a11> in <module>()
----> 1 vgg = Vgg16()
2 # Grab a few images at a time for training and validation.
3 # NB: They must be in subdirectories named based on their category
4 batches = vgg.get_batches(path+'train', batch_size=batch_size)
5 val_batches = vgg.get_batches(path+'valid', batch_size=batch_size*2)
/home/eagle/fastai/courses-master/deeplearning1/nbs/vgg16.pyc in __init__(self)
45 def __init__(self):
46 self.FILE_PATH = 'http://files.fast.ai/models/'
---> 47 self.create()
48 self.get_classes()
49
/home/eagle/fastai/courses-master/deeplearning1/nbs/vgg16.pyc in create(self)
137
138 fname = 'vgg16.h5'
--> 139 model.load_weights(get_file(fname, self.FILE_PATH+fname, cache_subdir='models'))
140
141
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/topology.pyc in load_weights(self, filepath, by_name)
2706 self.load_weights_from_hdf5_group_by_name(f)
2707 else:
-> 2708 self.load_weights_from_hdf5_group(f)
2709
2710 if hasattr(f, 'close'):
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/topology.pyc in load_weights_from_hdf5_group(self, f)
2792 weight_values[0] = w
2793 weight_value_tuples += zip(symbolic_weights, weight_values)
-> 2794 K.batch_set_value(weight_value_tuples)
2795
2796 def load_weights_from_hdf5_group_by_name(self, f):
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.pyc in batch_set_value(tuples)
1879 assign_ops.append(assign_op)
1880 feed_dict[assign_placeholder] = value
-> 1881 get_session().run(assign_ops, feed_dict=feed_dict)
1882
1883
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.pyc in get_session()
123 session = _SESSION
124 if not _MANUAL_VAR_INIT:
--> 125 _initialize_variables()
126 return session
127
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.pyc in _initialize_variables()
280 sess = get_session()
281 if hasattr(tf, 'variables_initializer'):
--> 282 sess.run(tf.variables_initializer(uninitialized_variables))
283 else:
284 sess.run(tf.initialize_variables(uninitialized_variables))
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
776 try:
777 result = self._run(None, fetches, feed_dict, options_ptr,
--> 778 run_metadata_ptr)
779 if run_metadata:
780 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
980 if final_fetches or final_targets:
981 results = self._do_run(handle, final_targets, final_fetches,
--> 982 feed_dict_string, options, run_metadata)
983 else:
984 results = []
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1030 if handle is None:
1031 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1032 target_list, options, run_metadata)
1033 else:
1034 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
1050 except KeyError:
1051 pass
-> 1052 raise type(e)(node_def, op, message)
1053
1054 def _extend_graph(self):
ResourceExhaustedError: OOM when allocating tensor with shape[25088,4096]
[[Node: random_uniform_13/RandomUniform = RandomUniform[T=DT_INT32, dtype=DT_FLOAT, seed=87654321, seed2=755436606, _device="/job:localhost/replica:0/task:0/gpu:0"](random_uniform_13/shape)]]
Caused by op u'random_uniform_13/RandomUniform', defined at:
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/__main__.py", line 3, in <module>
app.launch_new_instance()
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/kernelapp.py", line 478, in start
self.io_loop.start()
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 281, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 232, in dispatch_shell
handler(stream, idents, msg)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 397, in execute_request
user_expressions, allow_stdin)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-7-2b6861506a11>", line 1, in <module>
vgg = Vgg16()
File "vgg16.py", line 47, in __init__
self.create()
File "vgg16.py", line 134, in create
self.FCBlock()
File "vgg16.py", line 113, in FCBlock
model.add(Dense(4096, activation='relu'))
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/models.py", line 332, in add
output_tensor = layer(self.outputs[0])
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/topology.py", line 546, in __call__
self.build(input_shapes[0])
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/layers/core.py", line 798, in build
constraint=self.W_constraint)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/topology.py", line 418, in add_weight
weight = initializer(shape, name=name)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/initializations.py", line 66, in glorot_uniform
return uniform(shape, s, name=name)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/initializations.py", line 33, in uniform
return K.random_uniform_variable(shape, -scale, scale, name=name)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.py", line 634, in random_uniform_variable
low, high, dtype=tf_dtype, seed=seed)(shape)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/ops/init_ops.py", line 189, in __call__
dtype, seed=self.seed)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/ops/random_ops.py", line 236, in random_uniform
shape, dtype, seed=seed1, seed2=seed2)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/ops/gen_random_ops.py", line 263, in _random_uniform
seed=seed, seed2=seed2, name=name)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/eagle/anaconda3/envs/les1/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
self._traceback = _extract_stack()
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[25088,4096]
[[Node: random_uniform_13/RandomUniform = RandomUniform[T=DT_INT32, dtype=DT_FLOAT, seed=87654321, seed2=755436606, _device="/job:localhost/replica:0/task:0/gpu:0"](random_uniform_13/shape)]]
最佳答案
之后
nvidia-smi
最后一行将显示带有“pid”编号的进程
最后输入“pid”号
使用以下命令(最后的四位数字将是您自己的)
sudo kill -9 3096
关于python - 有些东西耗尽了大部分 GPU 内存，无法让我使用 Tensorflow 训练模型，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/48157558/