-
Notifications
You must be signed in to change notification settings - Fork 27
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
About testing result #25
Comments
I use the pretrained model provide in this project to test COCO test set, and eval performance is 'BLEU': [0.806718016311047, 0.6540980786273354, 0.5092295283787919, 0.3898375465182736], 'METEOR': 0.29228558925065895, 'ROUGE': 0.585628568332276, 'CIDEr': 1.3206302796307086. |
你好,能否提供一份特征?感激不尽!! |
我使用的特征来自https://github.com/luo3300612/image-captioning-DLCT
在 2022年3月15日星期二,hasky123 ***@***.***> 写道:
… 你好,能否提供一份特征?感激不尽!!
—
Reply to this email directly, view it on GitHub
<#25 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFRWDMICDIKLPORENFMHCOLVACWPFANCNFSM5QGNI5YQ>
.
Triage notifications on the go with GitHub Mobile for iOS
<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675>
or Android
<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
关于language model,您有没有使用我上传的的模型参数文件?还是您重新训练的? |
我使用的是上传的的模型参数文件 |
|
我check一下。 |
请问有结果了吗 |
你好,能更新代码吗,这个精度确实不对。 |
Hello Wan!I also use this open source code to train the RSTNet. However, at the end of cross-entropy training stage, I only get the CIDEr score about 103, is that normal? How much CIDEr score did you get at the end of cross-entropy training stage? How many epochs did you train during RL stage? Did you use other tricks that can tell me? |
I do not train the RSTNet. |
已更新 |
已更新 |
谢谢更新 |
Thanks for this amazing work.
Could you provide the inference captions of COCO test set by using the method proposed in this paper.
It is hard to download the features used in this paper due to its large size.
Thanks again.
The text was updated successfully, but these errors were encountered: