InvalidArgumentError Restoring from checkpoint failed

 tensorflow.python.framework.errors_impl.InvalidArgumentError
Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:  Assign requires shapes of both tensors to match. lhs shape= [48] rhs shape= [36] 

修改了MobileNet+yolo模型，在训练的时候没有出现错误，但是在评估的时候出现了错误代码如上

原因：在模型中加入了一个缩放变量，但是在评估部分代码没有将缩放变量添加，所以导致出现问题。
根源：评估模型与checkpoint文件中的模型不一致，导致无法导入模型