Bin Yan

@972821054 Hi, according to the number of classes of tracked objects in your dataset, you may need to change self.num_classes in the experiment file. By default, self.num_classes=8 for BDD100K and...

@972821054 It seems the version of mmcv is not compatible with that of your cuda. Please refer to the official website of mmcv for a compatible version.

@972821054 Yes, we use python 3.7

@972821054 if you want to train unicorn with convnext-tiny backbone for object tracking, use pretrained weights of [unicorn_det_convnext_tiny_800x1280](https://drive.google.com/file/d/11kLsIOp6jQEEM0ZmOvvsJW_RgjgCxuYZ/view?usp=sharing)

> @MasterBin-IIAU Thank you for your valuable suggestions. I have three questions to ask you. > > First: for motchallenge type training set (the organization is similar to mot16), but...

@972821054 There is no need to modify pre-trained weights. If there is only one class for your own dataset, please set self.num_classes to 1.

@972821054 Hi, we also trained and tested our method on the BDD100K dataset, a large-scale MOT benchmark on autonomous driving. The dataset contains 8 classes (pedestrian, rider, car, truck, bus,...

The result is shown [here](https://github.com/MasterBin-IIAU/Unicorn/blob/master/assets/MOT-BDD.png). The corresponding experiment and trained model are [unicorn_track_large.py](https://github.com/MasterBin-IIAU/Unicorn/blob/master/exps/default/unicorn_track_large.py) and [latest_ckpt.pth](https://drive.google.com/file/d/1P4__Xd1wvET5Sow21_zmOx3lupAuEWN6/view) respectively.

Hi, thank you for your interest to our work :) We still needs more time to sort out the complete code, including the searching and retraining. When everything is ready,...