Tensorflow由於版本問題出現的幾種錯誤及解決辦法
1、AttributeError: 'module' object has no attribute 'rnn_cell'
S:將tf.nn.rnn_cell替換為tf.contrib.rnn
2、TypeError: Expected int32, got list containing Tensors of type '_Message' instead.
S:由於tf.concat的問題,將tf.concat(1, [conv1, conv2]) 的格式替換為tf.concat( [conv1, conv2],1)
3、AttributeError: 'module' object has no attribute 'pack'
S:將pack替換為stack
4、ValueError: Only call `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...)
S:按照提示,需要將括號內的形參寫出,即(logits=pre, lables=tru)而非(pre,tru)
5、ValueError: Variable Wemb/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?
S:需要定義scope,雖然報錯可能是在optimizer處提示,但需要在定義模型時增加scope,即
with tf.variable_scope(tf.get_variable_scope()) as scope:
# model construction