search

CaptainEven / MCMOT

Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID
MIT License
386 stars 82 forks source link

Please provide installation steps #56

Closed abhaygargab closed 3 years ago

abhaygargab commented 3 years ago

Hello @CaptainEven ,

ThankYou for providing this code. I have followed the exact installation steps from https://github.com/ifzhang/FairMOT.

conda create -n MCMOT conda activate MCMOT conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0 -c pytorch cd ${MCMOT_ROOT} pip install -r requirements.txt We use DCNv2 in our backbone network and more details can be found in their repo. git clone https://github.com/CharlesShang/DCNv2 cd DCNv2 ./make.sh

Can you please confirm if you used the same steps?

I was able to successfully run the code from FairMOT repository, but i am facing issues while running the code in this repository.

ThankYou

sergiomallasen commented 3 years ago

@abhaygargab , were you able to perform a correct installation? Could you provide the steps? Thanks!