artest08
artest08
### 📚 The doc issue The announcement about the V2 improvements of RetinaNet, FasterRCNN and MaskRCNN has been made (Post Paper Architectural Optimization). Thanks for the amazing work. However, if...
### 🚀 The feature Thanks for the addition of Swin backbone to the repository. I think the added version is the V1 version of swin transformer. Is it possible to...
Hello, First of all, thank you for your great work. I want to ask a point in the implementation of input projection before the MaskHeadSmallConv in segmentation.py . The implementation...
Hello, I want to ask that whether you divide the image with 255 in normalization part? I could not see that part, I will be glad if you can show...
I want to ask one more thing about the estimation of discounted reward. The variable discounted reward always starts with zero. However, if the episode is not ended, should it...
I have noticed something but I am not sure, in preprocessing part, in load annotations, there is a line that if len(annots) == 0: annots = [[]] then, this is...
Thanks for the great work. I have read the paper and I think there is not enough detail about the implementation of hybrid matching. Or if there is, I could...
In /support/layer/roi_align.py, I am getting the error in the line of "from support import _C", such that _C cannot be imported?
Hello, I want to ask how you obtained the pre-trained weights? Is it the conversion from the Tensorflow weights or did you get it by training your-self? I also want...
Hello, Is it possible to learn frame numbers in the released pre-trained models? In the released model, What I understand is that there are 2^4 temporal stride which makes 16...