Faster-RCNN报错:ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshap

最近在用Faster-RCNN做目标检测

参考Analytics Vidhya的原文:https://www.analyticsvidhya.com/blog/2018/11/implementation-faster-r-cnn-python-object-detection/#comment-157499

参考阿里云云栖社区的翻译:https://yq.aliyun.com/articles/679245?utm_content=g_1000031076#

遇到问题:ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshape') with input shapes: [1,1,1,64], [].

 

解决方法:降低keras版本。CPU2.2.0可以,GPU2.1.6可以。

你可能感兴趣的:(机器学习)