tf-faster-rcnn跑demo.py出现InvalidArgumentError (see above for traceback): Assign requires shapes of bo
基于tf-faster-rcnn做图像识别时,使用自己的数据集。训练过程没有问题,然后跑demo的时候报:
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [4096,21] rhs shape= [4096,11]
[[Node: save/Assign_3 = Assign[T=DT_FLOAT, _class=["loc:@vgg_
原创
2020-09-01 09:12:16 ·
283 阅读 ·
0 评论