解决tensorflow报错ValueError: Variable conv1/weights already exists, disallowed.

早上在跑别人的tensorflow代码时报错：

Traceback (most recent call last):File "<ipython-input-23-712e8e1f026f>", line 1, in <module>runfile('C:/Users/peter/Downloads/tensorflow-mnist-cnn-master/mnist_cnn_train.py', wdir='C:/Users/peter/Downloads/tensorflow-mnist-cnn-master')File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfileexecfile(filename, namespace)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfileexec(compile(f.read(), filename, 'exec'), namespace)File "C:/Users/peter/Downloads/tensorflow-mnist-cnn-master/mnist_cnn_train.py", line 167, in <module>train()File "C:/Users/peter/Downloads/tensorflow-mnist-cnn-master/mnist_cnn_train.py", line 46, in trainy = cnn_model.CNN(x)File "C:\Users\peter\Downloads\tensorflow-mnist-cnn-master\cnn_model.py", line 22, in CNNnet = slim.conv2d(x, 32, [5, 5], scope='conv1')File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 183, in func_with_argsreturn func(*args, **current_args)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 1154, in convolution2dconv_dims=2)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 183, in func_with_argsreturn func(*args, **current_args)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 1057, in convolutionoutputs = layer.apply(inputs)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 805, in applyreturn self.__call__(inputs, *args, **kwargs)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\layers\base.py", line 362, in __call__outputs = super(Layer, self).__call__(inputs, *args, **kwargs)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 728, in __call__self.build(input_shapes)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\keras\layers\convolutional.py", line 161, in builddtype=self.dtype)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\layers\base.py", line 276, in add_weightgetter=vs.get_variable)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 565, in add_weightaggregation=aggregation)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\training\checkpointable\base.py", line 535, in _add_variable_with_custom_getter**kwargs_for_getter)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1467, in get_variableaggregation=aggregation)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 1217, in get_variableaggregation=aggregation)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 510, in get_variablereturn custom_getter(**custom_getter_kwargs)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 1744, in layer_variable_getterreturn _model_variable_getter(getter, *args, **kwargs)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\layers\python\layers\layers.py", line 1735, in _model_variable_getteruse_resource=use_resource)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 183, in func_with_argsreturn func(*args, **current_args)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\variables.py", line 297, in model_variableuse_resource=use_resource)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\arg_scope.py", line 183, in func_with_argsreturn func(*args, **current_args)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\contrib\framework\python\ops\variables.py", line 252, in variableuse_resource=use_resource)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 481, in _true_getteraggregation=aggregation)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 848, in _get_single_variablename, "".join(traceback.format_list(tb))))ValueError: Variable conv1/weights already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1717, in __init__self._traceback = tf_stack.extract_stack()File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3155, in create_opop_def=op_def)File "C:\Users\peter\AppData\Local\Continuum\anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py", line 454, in new_funcreturn func(*args, **kwargs)

我发现这是第一次跑，为什么会有模型重加载的问题。
然后我发现这是因为我在Spyder的Python控制台里跑的原因，Python的控制台会保存上次运行结束的变量。

解决方法1：重开一个控制台即可

解决方法2：在代码的开头加上一句

tf.reset_default_graph()

参考资料：
ValueError: Variable rnn/basic_rnn_cell/kernel already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?

Error in notebook: “ValueError: Variable conv1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope”

解决tensorflow报错ValueError: Variable conv1/weights already exists, disallowed.相关推荐

Variable conv1/weights already exists, disallowed. Did you mean to set reuse=True...tensorflow报错
在训练神经网络模型使用tensorflow时,training模块训练多次会出现报错如: 1,Variable conv1/weights already exists, disallowed. Di ...
ValueError: Variable conv1/weights already exists.
跑TensorFlow程序的过程中出现了错误,解决之后再次跑时,报如下错误: ValueError: Variable conv1/weights already exists, 原因: 这是因为我在 ...
解决tensorflow报错：AttributeError: module ‘tensorflow.keras.backend‘ has no attribute ‘get_session‘ 问题
欢迎大家关注笔者,你的关注是我持续更博的最大动力原创文章,转载告知,盗版必究解决tensorflow报错:AttributeError: module 'tensorflow.keras.back ...
解决yolov5 报错 ValueError: not enough values to unpack (expected 3, got 0)
解决yolov5 报错 ValueError: not enough values to unpack (expected 3, got 0) *注意报错提示 :labels, shapes, sel ...
解决statsmodels报错ValueError: Pandas data cast to numpy dtype of object.
完整报错是:ValueError: Pandas data cast to numpy dtype of object. Check input data with np.asarray(data). ...
解决qcut报错ValueError: Bin labels must be one fewer than the number of bin edges
qcut这个函数就挺迷的,今天运行之前的代码居然报错了,报错信息如下: ValueError: Bin labels must be one fewer than the number of bin ...
tensorflow报错a Variable name or other graph key that is missin, Restoring from checkpoint failed. T
报错 Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key t ...
解决Numpy 报错 ValueError: zero-size array to reduction operation maximum which has no identity
这是因为numpy对一个空的array做运算操作造成的,如: x = np.array([]) # x + 1 # 会报错建议在代码中可以改为: if x.size == 0:print('x.si ...
Tensorflow报错：ValueError: Trying to share variable ..., but specified shape ... and found shape ...
Tensorflow报错:ValueError: Trying to share variable CON/conv2/W, but specified shape (3, 3, 128, 256) ...

解决tensorflow报错ValueError: Variable conv1/weights already exists, disallowed.

解决方法1：重开一个控制台即可

解决方法2：在代码的开头加上一句

解决tensorflow报错ValueError: Variable conv1/weights already exists, disallowed.相关推荐

最新文章

热门文章