今天在用tensorflow开始训练时,出现这种问题,模型是inceptionv3,请问该如何解决?
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= [5] rhs shape= [1001] [[Node: save/Assign_20 = Assign[T=DT_FLOAT, _class=["loc:@InceptionV3/Logits/Conv2d_1c_1x1/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](InceptionV3/Logits/Conv2d_1c_1x1/biases, save/RestoreV2:20)]] |
|
沙发#
发布于:2019-03-09 22:35
楼主,研究的这块挺有意思的,可惜没有做过这块。根据你的问题提示:大概查了一下
可以看看:https://github.com/tensorflow/tensorflow/issues/6883 看这篇文章:https://www.twblogs.net/a/5b7f38052b717767c6ae626d/ ,上说 Just delete the previous files in the output folder(只需删除输出文件夹中以前的文件). 没有环境,不能测试,还望对楼主有所帮助 |
|
|