DRNet

DRNet copied to clipboard

Hello, I trained DRNet on the HT21 dataset, and tested it using the best weight file. However, the evaluation metrics I obtained are significantly different from the values you provided....

bbhbbxwy

how generate dataset

2

Thank you very much for providing the algorithm. I would like to inquire about how to generate the dataset. I noticed there are .txt data files in the materials you...

andydufresn

missing label for SENSE dataset

6

I download the SENSE dataset from baidu, but there is no label for scene IMG_4696_cut_03.txt at frame 000084.jpg and 000085.jpg. Can anyone provide GT of these two frames? thanks!

linthmwan

How could I run the repo on a video and see the result?

4

How could I run the repo on a video and see the result? I want to test a video like https://www.bilibili.com/video/BV1cY411H7hr/.

munaiyi719

hi I ran the code "train.py" on my server and got this error. I searched and found that it was added in PyTorch 1.8.0, so I upgraded PyTorch. However, I...

shmorish

what is the target means in def forward(self, img, target=None)

1

`def forward(self, img, target=None):` what does the target stand for in this function argument? Is there a sample or description? thanks

john81923

Hellow，I ran the train.py file but encountered the following problem.How do I fix it? dataset is HT21, images num is 5312 train/HT21-01 Using /home/liuwenjie/.cache/torch_extensions/py38_cu118 as PyTorch extensions root... Detected CUDA...

0317lwj

Hello, I am curious about how the VScrowd dataset is partitioned during DRnet training. I noticed that the authors of VScrowd currently name each folder as train_xx, test_xx, but in...

PengqiH

Hi, I would like to know from where I can get the ground truth of the test folder of the HT21 dataset, thanks!

0317lwj