报错InvalidArgumentError (see above for traceback): Restoring from checkpoint failed

报错详情：
使用faster-rcnn训练自己的模型，下载使用别人的代码
这份代码
运行python tools/demo.py报错
如下：

Traceback (most recent call last):File "tools/demo.py", line 145, in <module>saver.restore(sess, tfmodel)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 1312, in restoreerr, "a mismatch between the current graph and the graph")
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= [2048,84] rhs shape= [2048,20][[node save/Assign_1 (defined at tools/demo.py:144) ]]Caused by op 'save/Assign_1', defined at:File "tools/demo.py", line 144, in <module>saver = tf.train.Saver()File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 832, in __init__self.build()File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 844, in buildself._build(self._filename, build_save=True, build_restore=True)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 881, in _buildbuild_save=build_save, build_restore=build_restore)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 513, in _build_internalrestore_sequentially, reshape)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 354, in _AddRestoreOpsassign_ops.append(saveable.restore(saveable_tensors, shapes))File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saving/saveable_object_util.py", line 73, in restoreself.op.get_shape().is_fully_defined())File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/state_ops.py", line 223, in assignvalidate_shape=validate_shape)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_state_ops.py", line 64, in assignuse_locking=use_locking, name=name)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helperop_def=op_def)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_funcreturn func(*args, **kwargs)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3300, in create_opop_def=op_def)File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 1801, in __init__self._traceback = tf_stack.extract_stack()
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:Assign requires shapes of both tensors to match. lhs shape= [2048,84] rhs shape= [2048,20][[node save/Assign_1 (defined at tools/demo.py:144) ]]

原因：

#加载模型
demo.py文件
net.create_architecture("TEST", 21, tag='default', anchor_scales=[8, 16, 32])
对比test_net.py文件
net.create_architecture("TEST", imdb.num_classes,tag='default',anchor_scales=cfg.ANCHOR_SCALES,anchor_ratios=cfg.ANCHOR_RATIOS)

对比：21 和 imdb.num_classes
可知这个位置的参数代表种类数目，要改成自己的。

报错InvalidArgumentError (see above for traceback): Restoring from checkpoint failed相关推荐

tensorflow报错a Variable name or other graph key that is missin, Restoring from checkpoint failed. T
报错 Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key t ...
docker 报错 /usr/bin/docker-current: Error response from daemon: driver failed programming external
现象:centos7 下docker启动容器报错 /usr/bin/docker-current: Error response from daemon: driver failed programm ...
【IDEA 报错 ERROR 16720 --- [ restartedMain] o.a.coyote.http11.Http11NioProtocol : Failed to sta】
提示:文章写完后,目录可以自动生成,如何生成可参考右边的帮助文档 IDEA 报错 ERROR 16720 - [ restartedMain] o.a.coyote.http11.Http11NioP ...
Mac安装HomeBrew及update报错Error: Fetching /opt/homebrew/Library/Taps/homebrew/homebrew-cask failed
Mac安装HomeBrew及update报错Error: Fetching /opt/homebrew/Library/Taps/homebrew/homebrew-cask failed! 报错运 ...
DNS服务--nslookup解析报错UnKnown 找不到 www.xxx.com: Server failed
- 问题:nslookup www.xxx.com 报错 *** UnKnown 找不到 www.xxx.com: Server failed - 问题所在 /var/named/下面xxx.com. ...
NotFoundError: Restoring from checkpoint failed. 解决
遇到的问题: tensorflow版本:tensorflow1.13.1-gpu 今天在学习tensorflow的模型保存和载入中出现以下BUG NotFoundError: Restoring fr ...
tensorflow Restoring from checkpoint failed
发生异常: tensorflow.python.framework.errors_impl.InvalidArgumentError Restoring from checkpoint failed. ...
Spyder：NotFoundError: Restoring from checkpoint failed.
Tensorflow加载模型错误: NotFoundError: Restoring from checkpoint failed. This is most likely due to a Vari ...
在跑FIA时遇到的问题Restoring from checkpoint failed. This is most likely due to a Variable name or other gra
问题: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key ...

报错InvalidArgumentError (see above for traceback): Restoring from checkpoint failed

报错InvalidArgumentError (see above for traceback): Restoring from checkpoint failed相关推荐

最新文章

热门文章