wutong16/DistributionBalancedLoss
[ ECCV 2020 Spotlight ] Pytorch implementation for "Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets"
Python
Issues
- 0
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [64, 109]], which is output 0 of SigmoidBackward0, is at version 1; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!
#20 opened by Surendradhaka123 - 0
How to use the ResampleLoss?
#19 opened by crazy-zxx - 0
About code implementation of eq7
#18 opened by saishkomalla - 2
About Class aware sampler
#17 opened by zhandand - 0
FileNotFoundError: [Errno 2] No such file or directory: '/mnt/SSD/det/coco/annotations/instances_train2017.json'
#16 opened by AL-Yan - 2
- 2
- 0
- 0
bug: args.gpus is missing
#13 opened by VamosC - 2
大佬,这个方法可以用在one stage模型中吗(yolov5)
#12 opened by CangHaiQingYue - 0
How to reproduce the baseline mAP on VOC dataset
#11 opened by zjhdxh - 4
How to use in my own dataset?
#10 opened by Jacobew - 2
Lower mAP when training on VOC
#9 opened by Kevinz-code - 1
- 0
- 1
- 1
Support multi-GPU training?
#4 opened by chen-judge - 1
Question regarding the model
#3 opened by nurmanmus - 4
problem of train set and experiment
#2 opened by valencebond - 1
formulation error in Eq 7
#1 opened by valencebond