报错:Input ‘split_dim’ of ‘Split’ Op has type float32 that does not match expected type of int32
x = tf.split(0, n_steps, x) # tf.split(axis, num_or_size_splits, value)
修改为
x = tf.split(x, n_steps, 0) # tf.split(value, num_or_size_splits, axis)
由于 tensorflow 版本不同,API 的调用方式有写改变
ValueError: Variable basic/rnn/basic_lstm_cell/kernel does not exist, or was not created with tf.get_variable().
Did you mean to set reuse=tf.AUTO_REUSE in VarScope?
这表示 方法所需参数 与实际参数不符
'module' object is not callable
这表示 原本是一个类,被当做方法来调用