Wang Zhaodi

> coco格式可能还是有些问题，可以提供一个小的annotation上来。 那請問如果是自己的數據集，到底要怎麼做呢？

> I am also experiencing this issue. It appears pull requests #121 and #122 will solve this issue. Can somebody pull these in? Hello! I modify my code like #121...

Did you solve the problem? I also meet the problem assert rois.size(0) > 0. And I found that image 2389060.jpg only have one ground truth bounding box, thus the predcls...

I have the same question！

I see the code！ I found that maybe the author used files in '/end2end_rgbt_tracking/mfDiMP/ltr/train_settings/seq_tracking/sdlearn_300_onlytestloss_lr_causal_mg30_iou_nocf_res50_lfilt512_coco.py' to train the RGB modality tracker. And then use the pretrained model in epoch 40 to...

> > I see the code！ I found that maybe the author used files in '/end2end_rgbt_tracking/mfDiMP/ltr/train_settings/seq_tracking/sdlearn_300_onlytestloss_lr_causal_mg30_iou_nocf_res50_lfilt512_coco.py' to train the RGB modality tracker. And then use the pretrained model in epoch...