部署SSD遇到的问题及解决办法

问题一

tensorflow版本问题

WARNING:tensorflow:Entity <bound method SeparableConv2D.call of <tensorflow.python.layers.convolutional.SeparableConv2D object at 0x0000011F446E9668>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method SeparableConv2D.call of <tensorflow.python.layers.convolutional.SeparableConv2D object at 0x0000011F446E9668>>: AssertionError: Bad argument number for Name: 3, expecting 4

解决办法：
卸载掉高版本的gast
再pip install gast==0.2.2
原文链接：Tensorflow代码报错：call of

问题二

Assign requires shapes of both tensors to match. lhs shape= [3,3,512,68] rhs shape= [3,3,512,8]
	 [[node save/Assign_18 (defined at D:/personal/new_packages/tensorflow-ssd-win7-2d_/test.py:66) ]]
Errors may have originated from an input operation.
Input Source operations connected to node save/Assign_18:
 ssd_300_vgg/block4_box/conv_cls/weights (defined at D:personalnew_packagestensorflow-ssd-win7-2d_netsssd_vgg_300.py:426)

解决办法：
涉及类别classes的地方，查看是否相匹配。

问题三

“拒绝访问”
解决办法：

1. 若某程序占用，需解决占用；

最后

以上就是爱笑蚂蚁为你收集整理的部署SSD遇到的问题及解决办法的全部内容，希望文章能够帮你解决部署SSD遇到的问题及解决办法所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。