我正在用Hyperopt对神经网络进行超参数优化。在这样做时,经过一些迭代之后,我得到了一个MemoryError异常
到目前为止,我尝试在使用完所有变量后清除它们(为它们分配无列表或空列表,有更好的方法吗?)打印所有的local()、dirs()和globals()以及它们的大小,但是这些计数永远不会增加,而且大小非常小。你知道吗
结构如下所示:
def create_model(params):
## load data from temp files
## pre-process data accordingly
## Train NN with crossvalidation clearing Keras' session every time
## save stats and clean all variables (assigning None or empty lists to them)
def Optimize():
for model in models: #I have multiple models
## load data
## save data to temp files
trials = Trials()
best_run = fmin(create_model,
space,
algo=tpe.suggest,
max_evals=100,
trials=trials)
在X次迭代之后(有时它完成第一个100次并转移到第二个模型),它抛出一个内存错误。 我的猜测是,一些变量仍保留在内存中,我没有清除它们,但我无法检测到它们。你知道吗
编辑:
Traceback (most recent call last):
File "Main.py", line 32, in <module>
optimal = Optimize(training_sets)
File "/home/User1/Optimizer/optimization2.py", line 394, in Optimize
trials=trials)
File "/usr/local/lib/python3.5/dist-packages/hyperopt/fmin.py", line 307, in fmin
return_argmin=return_argmin,
File "/usr/local/lib/python3.5/dist-packages/hyperopt/base.py", line 635, in fmin
return_argmin=return_argmin)
File "/usr/local/lib/python3.5/dist-packages/hyperopt/fmin.py", line 320, in fmin
rval.exhaust()
File "/usr/local/lib/python3.5/dist-packages/hyperopt/fmin.py", line 199, in exhaust
self.run(self.max_evals - n_done, block_until_done=self.async)
File "/usr/local/lib/python3.5/dist-packages/hyperopt/fmin.py", line 173, in run
self.serial_evaluate()
File "/usr/local/lib/python3.5/dist-packages/hyperopt/fmin.py", line 92, in serial_evaluate
result = self.domain.evaluate(spec, ctrl)
File "/usr/local/lib/python3.5/dist-packages/hyperopt/base.py", line 840, in evaluate
rval = self.fn(pyll_rval)
File "/home/User1/Optimizer/optimization2.py", line 184, in create_model
x_train, x_test = x[train_indices], x[val_indices]
MemoryError
我花了几天时间才弄明白,所以我会回答我自己的问题,以节省任何人遇到这个问题的时间。你知道吗
通常,当对Keras使用Hyperopt时,
create_model
函数的建议return
是这样的:但是在大型模型中,有许多求值,您不希望返回每个模型并将其保存在内存中,您所需要的只是一组给出最低
loss
的超参数通过简单地从返回的dict中删除模型,解决了每次求值时内存增加的问题。你知道吗
相关问题 更多 >
编程相关推荐