Kepan Nan

hi,when i ran th code on fsod it was fine,but i got this error when i trained my dataset,could you give me some advice? 

RefCOCO/+/g json files

8

Thanks for your great work! Can you provide the RefCOCO/+/g json files? I din't find them in this repository. 

The robustness of model is not good

3

It seems that the robustness of model is not good. There is a big performance gap between models trained by the same code. Can this prolem be fixed by increase...

possible deadlock in dataloader

3

HI, When I train a model with num_workers>1, it is possible to stuck on this line: https://github.com/scutpaul/DANet/blob/f0bc57d9b2641c4dda9ce70e2c6f240ce2789069/test_DAN.py#L137 Then I debug and find that it stucks on this tow lines: https://github.com/scutpaul/DANet/blob/f0bc57d9b2641c4dda9ce70e2c6f240ce2789069/libs/dataset/YoutubeVOS.py#L156...

question about experiments of the paper

1

I wonder if the test result based on epoch_100.pth.tar or model_best.pth.tar

static images datasets

1

Is all static images datasets for Pre-training the training set or both training and val set? Is static images datasets COCO for Pre-training the coc2014 training set or coco2017 training...

dataset

2

Hi, the link (https://drive.google.com/file/d/1Lj-oBzBNUsAqA9y65BDrSQxirV8S15Rk/view?usp=sharing) and [SegmentationClassAug] are invalid, could you provide a new one. Thanks.

The generated videos are shaking and unstable.

4

I trained a stdit model with webvid. The generated videos are shaking and unstable. Can you give me some reasons or suggestions？Is there some training tricks? https://github.com/hpcaitech/Open-Sora/assets/82510548/57a06b2f-6dc4-4752-af4d-9f10625ba4e9 https://github.com/hpcaitech/Open-Sora/assets/82510548/5906d127-e874-442e-bdd9-fa563502d5f5 https://github.com/hpcaitech/Open-Sora/assets/82510548/49c48e82-ba2b-4748-9b26-5346ca4f0524

freeze the non-temporal parameters

1

Hi, I have a question. Should I freeze the non-temporal parameters during training? Thank you!

Training of image based few shot methods

1

Hi, how to get results(Table 3) of image based few shot methods(PMMs, PFENet and PPNet) in paper? Should I use their pretrained models to test on Youtube-VIS dataset, or train...