deep_sort_pytorch
deep_sort_pytorch copied to clipboard
MOT using deepsort and yolov3 with pytorch
Hi @ZQPei, Could you share the evaluation result of modified Deep SORT model on MOT16? Thanks.
I was surprised by the model file ( ckpt.t7 )provided , which dataset was the model training on ? Market1501 or Mars dataset
PS D:\ML_Data\4_2_ZQPei_deep_sort_pytorch\ZQPei_deep_sort_pytorch> python yolov3_deepsort_eval.py D:\ML_Data\4_2_ZQPei_deep_sort_pytorch\ZQPei_deep_sort_pytorch\utils\parser.py:23: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. self.update(yaml.load(fo.read())) 2021-02-10 17:10:54 [INFO]: start seq:...
I don't understand the evaluate.py script. What is the end of this code line --> scores = qf.mm(gf.t()) ? I don`t know why do you multiply arrays.
RuntimeError: No such operator torchvision::nms How to solve this?
Hello, The evaluation protocol is based on "query" and "gallery", taken from MARS dataset. But after downloading the dataset, I have only "train" and "test" folders. I am missing where...
Hello, I'm trying to train a custom dataset with this model, and whatever i try, the validation loss is always high. Even with MARS Dataset.  This here would be...
您好! 假如我现在已经有了每一帧的检测结果和提完的特征,我想送入sort部分进行跟踪,请问sort部分有加速的可能吗?也就是非深度模型部分的加速。