Simon

Please use this [link](http://bunwell.cs.ucl.ac.uk/ipinyou.contest.dataset.zip) for downloading the **ipinyou.contest.dataset.zip**.

> I trained the model you provided on the GoPro dataset. I trained 3000 Epoch with CharbonnierLoss and Edge loss as MPRNet code and I also use same scheduler as...

I think you should add the key MODEL.PROPOSAL_GENERATOR.HID_CHANNELS in this file **py-bottom-up-attention/detectron2/config/defaults.py**

Thanks a lot. Now I have a clear mind for my work.

Also, i have two small questions. (a) I have tested custom images (MSCOCO 2014 train) on SGDet model, and i got two files: custom_data_info.json and custom_prediction.json. In custom_prediction.json, there are...

Hi, in README, you said, "the features extracted from this repo is compatible with LXMERT code and pre-trained models here", that is say, if i want to directly use the...

你好，我最近也在研究这个。我也是想使用36 fixed bottom up feature来利用pretrained model生成它们之间的关系。按理说，应该是可以直接从bottom up feature（包含gt_box和labels的）直接生成关系的（直接使用pretrained model，但是这里的输入就不是images了，而是需要自己做一些修改（对dataloader做修改），直接用 bottom up feature（包含gt_box和labels的）作为输入。这是我的理解。

Yes it is. BTW, i have some questions. (a) 我从这个链接[https://github.com/peteanderson80/bottom-up-attention](url)获得的bottom up features只有bounding box和region features， 没有class 信息，请问包含的class label信息的bottom up features可以在哪里找到呢？ （另外如果还有attribute信息的话更好）(b) 另外我在做SGDet任务的时候， 使用custom images（VG数据集）作为输入的时候，代码里出现了bug，有以下三种都出现过： （1）AttributeError: 'VGDataset' object has no attribute 'ind_to_classes'...

Thanks a lot and thanks to [https://github.com/airsplay/py-bottom-up-attention](url) which highly caters to my desire. In this repro, it is easy to extract the 36 fixed features, bounding boxs, class labels and...

BTW, i find that the extratced features based on this repro [https://github.com/airsplay/py-bottom-up-attention](https://github.com/airsplay/py-bottom-up-attention) slightly differ from that in original repro [https://github.com/peteanderson80/bottom-up-attention](https://github.com/peteanderson80/bottom-up-attention). The author has explained the reason. Also, if i want...