CornerNet-Lite
CornerNet-Lite copied to clipboard
how to solve the issue "None type has attribute shape"
我是按照作者的目录放置的文件,代码也不会有错,但是运行的时候出现了“None type has attribute shape”后来同事提醒发现,应该把minival2014里面的图片全部复制然后放到trainval2014里面合并在一块。然后就训练成功跑通了。
make sure your image data dir is right in " CornerNet-Squeeze.json -->data_dir" and "dbs\coco.py"
为什么我合并了还是这个错误。。。哭了
就是应该合并的,这个数据集的使用和faster-rcnn,你尝试将中间结果输出,比如将imagepath输出。一般出现这个错误是因为没有读到图片。
---Original--- From: "Sherry0815"<[email protected]> Date: Tue, Dec 10, 2019 11:22 AM To: "princeton-vl/CornerNet-Lite"<[email protected]>; Cc: "Comment"<[email protected]>;"zhiyingf"<[email protected]>; Subject: Re: [princeton-vl/CornerNet-Lite] how to solve the issue "None type has attribute shape" (#97)
为什么我合并了还是这个错误。。。哭了
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
标签和图片有误