kakaobrain / scrl Goto Github PK

Thanks for your great repo! I have the following questions about the code:

1. In both online and target network, the feature map is learned before finding ROIs. I would like to know how we can extract these feature maps?
2. In your studies you mentioned that you used this work in localization tasks (object detection with Faster RCNN). Do you mind to share some sample scripts that how you used your method for object detection?

Thanks,

i dont know where to set dataset, hope you could describe this more clearly !thank you very much

how about the results of using scrl for classification task? do you have the results?

First of all , i am very interested in your paper.
Since your model is based on BYOL, I think the BN layer is very important in projector and predictor, and it's beneficial from large batch-size.
Since your code is working with DDP, i didn't find the Sync_Batchnorm.....i think it's weird.... If u don't use Sync-BN, so the BN is calculated only in each single gpu but not share with other gpus.
I think maybe i make a mistake, so do ur codes using Sync_Batchnorm in default? Should we use SyncBN?
Hope anyone can answer my question, Thx!

Hello, Thanks for sharing your codes ~
I try to train on VOC2012 without label to get the pretrained model, and then finetune with VOC2012 detection label. The result is very poor, but the result should be better Since pretrain dataset and finetune dataset is the same. Did you tried this or do you have any idea that what's the reason?

Paper p. 12
Table A3. COCO detection using Faster R-CNN, ResNet-50-FPN.Upstreams are trained with the unlabeled COCO dataset with 2000epochs.

In your code, it have to use labels like classification task, but in the paper, you described you used unlabeled COCO dataset.
Doesn't it care about labels? Then, can I use like this?

data/mydataset/0/image_0.jpg
data/mydataset/0/image_1.jpg
data/mydataset/0/...
data/mydataset/1/image_0.jpg
data/mydataset/1/image_1.jpg
data/mydataset/1/...

(I changed imageNet to imageFolder.)

Thanks for sharing such wonderful work! it's so amazing! Now I am trying to reproduce your work, but I meet some problem about generating bboxes in intersection area. According to your paper, you use some operation similar to RandomResizedCrop to generate two views and compute intersection between these two views, but how to ensure these two views always have overlaps. In addition, I found that even if two views have overlaps, there are some image which can not generate enough bboxes, for example, 10. Is there some other operation to solve this problem? Can you give me some suggestion?

After the upstream training~
when i load the "checkpoint_best.pth", I got an error like [enforce fail at inline_container.cc:209]. file not found: archive/data/3259494704. I don't know exactly why the file was somehow corrupted.

Great work, I can't wait to try it！