ValueError：變量vgg_16/conv1/conv1_1 /權重已存在，不允許

Question

嘗試使用現有權重時，我收到了這種錯誤消息。

ValueError: Variable vgg_16/conv1/conv1_1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at: 

    File "/usr/local/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 217, in variable 
    use_resource=use_resource) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args 
    return func(*args, **current_args) 
    File "/usr/local/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 262, in model_variable 
    use_resource=use_resource) 

代碼：https://github.com/datomnurdin/tensorflow-image-segmentation/blob/master/index.ipynb

請指點。謝謝。

Answer 1

您不能創建兩個具有相同名稱的Tensorflow變量。如果您不再需要任何舊變量，則可以使用tf.reset_default_graph()來重置圖形。否則，你需要定義示波器：https://www.tensorflow.org/programmers_guide/variable_scope