qdtrack
qdtrack copied to clipboard
SysCV
Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)
Thank you for your great work. when i tested on MOT17，I got an error like this: ModuleNotFoundError: No module named 'qdtrack'  And what is the '[--out ${RESULT_FILE}]'? And how...
Greetings, I am currently using qdtrack in python 3.8, Cuda 11 based environment for RTX 3090 GPU. While training as well as testing, I am getting this error. All required...
The detection label downloaded from the official website of BDD is a JSON file for each image. Without the det_${SET_NAME}. json you said in the document, how to obtain this...
I am trying to reproduce the inference as described in your repo. I use single-gpu testing and run the following command in my terminal: python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out test.pkl...
When I convert det_train.json to det_train_cocofmt.json, I meet this problem in picture. But I can convert det_val.json and track successfully. I'm confused this situation.  
Can you provide a quick example that shows how to do inference per image. I had a look at your [inference api](https://github.com/SysCV/qdtrack/blob/6f8a4e17f381fe6a5e4f90519305b32115927c73/qdtrack/apis/inference.py) but I cannot understand how to pass my...
I have been getting this warning. I had copied the pretrained code snippet from backbone and added it to neck and head modules. When I am training the model, I...
Could you release some config about Waymo Detection & Tracking ??
Hi, Can you have some instructions about Waymo MOT experiment beside BDD100k & TAO dataset?
Greetings, Is it possible to initialize neck and heads with pre-trained weights just like how it is possible for backbone ? If not, then how can I modify the config/scripts...