运行predict出现ValueError: Dimension 0 in both shapes must be equal, but are 12800 and 800. Shapes are [12800,500] and [800,500]. for 'Assign_4' (op: 'Assign') with input shapes: [12800,500], [800,500].

[shakey-cuimiao]

[tslgithub]

我看看哈

[Chen65010445]

我在测试的时候也出现了这个问题 请问您解决了吗

[itismeJH]

测试的时候，图片的尺寸和训练的时候不一样

------------------ 原始邮件 ------------------ 发件人: "tslgithub/image_class" <[email protected]>; 发送时间: 2020年8月14日(星期五) 下午2:21 收件人: "tslgithub/image_class"<[email protected]>; 抄送: "Subscribed"<[email protected]>; 主题: Re: [tslgithub/image_class] 运行predict出现ValueError: Dimension 0 in both shapes must be equal, but are 12800 and 800. Shapes are [12800,500] and [800,500]. for 'Assign_4' (op: 'Assign') with input shapes: [12800,500], [800,500]. (#19)

我在测试的时候也出现了这个问题 请问您解决了吗

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[Chen65010445]

但是我的测试图片和训练图片是一样的呀，因为是用程序直接从一个数据集随机拆出来的 难道normal_size也要做对应设置么？