Mask heads and COCO_dataset_api

[lzhnb]

I've convert the coco_dataset into voc_type, but i meet some trouble during training.

Can you complete the model with mask heads and the metadataset api for coco_dataset, if you can release the coco_task's weight, i'll be very thankful.

Thanks

[yanxp]

As for mask head, we used Detectron.pytorch.

[lzhnb]

And the coco_dataset? It seems need to convert coco into voc's type

[Ze-Yang]

@lzhnb Would you also like to reproduce the result in COCO dataset or COCO to VOC setting? Maybe we can tackle it together. Here is my email [email protected]

[lzhnb]

@lzhnb Would you also like to reproduce the result in COCO dataset or COCO to VOC setting? Maybe we can tackle it together. Here is my email [email protected]

I can't send email to you, and my email is [email protected]

[Ze-Yang]

Sorry. There is a small mistake with my email. The correct one is [email protected]. Thanks.

Best, Ze

------------------ 原始邮件 ------------------ 发件人: "lzhnb"<[email protected]>; 发送时间: 2019年10月27日(星期天) 下午2:08 收件人: "yanxp/MetaR-CNN"<[email protected]>; 抄送: "也许べ已没有也许"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [yanxp/MetaR-CNN] Mask heads and COCO_dataset_api (#9)

@lzhnb Would you also like to reproduce the result in COCO dataset or COCO to VOC setting? Maybe we can tackle it together. Here is my email [email protected]

I can't send email to you, and my email is [email protected]

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

[zb1439]

Hi @yanxp, could you clarify which mask branch fashion of detectron are you using in your model, as mask branch of detectron has many alternatives. Looking forward to your reply :-)

[chronbird]

Hi @yanxp , can you please explain how you got your COCO instance segmentation results in your paper? I cannot find the code related to that. Thank you so much in advance :)