joeyslv comments

Results 8 comments of


                                            joeyslv

Custom object-detection dataset support

Did you solve this @sharmalakshay93 ?

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

And when I was slicing through data in the coco format, was `licenses` label missing from my data, was it necessary? ``` (arknights) E:\Object-Detection\SoftTeacher>python tools/dataset/semi_coco.py --percent 2 --seed 1 --data-dir...

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

i set the licenses and info = [] it can split my dataset but `unsup_loss_rpn_cls` and` unsup_loss_rpn_bbox` ==0 ,Can someone please tell me how to fix this？ ``` new_anno =...

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

> Hello, how did u solve the qusetion "unsup_loss_bbox: 0.0000"? 没有，他们说是数据集的问题，但是我仔细检查了还是不行，放弃了

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

> > > Hello, how did u solve the qusetion "unsup_loss_bbox: 0.0000"? > > > > > > 没有，他们说是数据集的问题，但是我仔细检查了还是不行，放弃了 > > 好的，谢谢您我最近在linux上重新装了一下环境跑通了发现不是我的数据有问题非监督的损失"unsup_loss_bbox: 0.0000"需要训练等更新了教师参数才有你可以把伪标签阈值设定得低一些代码里初始是0.9

joeyslv

Custom object-detection dataset support

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

is dataset have transform_matrix？unsup_loss_bbox: 0.0000 when i try to train, I wanted to know if it was because of the data set, but my data set was fully trained and calculated on the supervised model？

error: legacy-install-failure

请问一下Dense teacher提出的DPL是否其实只是针对预测的类别分支？

The Threshold Problem of GMM