Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如何制作自己得数据集 #36

Closed
xueyingliu opened this issue Aug 21, 2017 · 8 comments
Closed

如何制作自己得数据集 #36

xueyingliu opened this issue Aug 21, 2017 · 8 comments

Comments

@xueyingliu
Copy link

您好,用您的代码跑通了pascal voc数据集,现在我想训练自己得数据,数据集标注时候类别和颜色是怎么对应得呀?

@lukk47
Copy link

lukk47 commented Sep 2, 2017

Please check the VOC specification, no color is needed. The classes are labeled from 0 to 20

@xingbotao
Copy link

你跑的是哪个模型呢?我在跑Desnet_FCN时,有一个错误,value_error: cannot feed value of shape(16,320,320,1) for tensor u reshape_1_target:0', which has shape'(?,?)'

@xueyingliu
Copy link
Author

@xingbotao 我跑的是AtrousFCN_Vgg16_16s,你的错误看起来好象是图片尺寸不符合网络吧,感觉可以改一下target_size什么的

@zwlshine
Copy link

zwlshine commented Nov 9, 2017

@xueyingliu 你好,请教一下,我运行的时候总是出错:ValueError: If printing histograms, validation_data must be provided, and cannot be a generator.
而且在函数model.fit_generator()中验证集validation_data给注释掉了。取消注释也出现这个错误。

@xueyingliu
Copy link
Author

@zwlshine 这个错误我好像也遇到过,当时觉得是没有必要printing histograms,就把相关的语句给注释掉了。

@zwlshine
Copy link

zwlshine commented Nov 13, 2017

@xueyingliu 非常感谢你!整个例子都跑通了。感觉这个错误跟tensorflow的一些应用有关系,不过我还没学tensorflow。再次谢谢你。

@xueyingliu
Copy link
Author

@zwlshine 不客气,一起加油!

@simonsayshi
Copy link

@xueyingliu 请问target_size代表什么?我跑的时候提示data shape 和label shape不一致,data shape 和设置的target_size是一样的,那么label shape怎么设置?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants