maskrcnn n the checkpoint. Original error:

1 问题

tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from c
    InvalidArgumentError (see above for traceback): 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:
  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:
           531 
           532 Assign requires shapes of both tensors to match. lhs shape= [27,768] rhs shape= [10,768]
           533      [[{
     {
     node save/Assign_200}} = Assign[T=DT_FLOAT, _class=["loc:@output_weights"], use_locking=true, validate        _shape=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](output_weights,
   save/RestoreV2/_403)]]

2 问题分析
可能就是output的checkpoint中有数据的问题，导致出现了shape不一致的情况，上次运行其他训练任务的时候生成的模型和现在也生成的模型的shape不一致，所以这里需要在运行前先清空之情的output。

3 问题解决

--output_dir=../output/
rm  output -rf