Cuogeihong

While training the RetinaNet baseline using your splited VisDrone dataset, I find the processed dataset has only 9 categories. In the [visdrone/data_prepare.py](https://github.com/ChenhongyiYang/QueryDetPyTorch/blob/main/visdrone/data_prepare.py), I find these codes ```def make_json(images, annotations, new_label_json):...

Cannot reproduce VBench-I2V results on CogVideoX-5b-I2V

4

We highly appreciate your continuous contribution in t2v, i2v benchmark Following the guidance, we install the specified environment (cuda 12.1, transformers 4.33.2, torch 2.5.1). We download cogvideox-5b-i2v results from google...