dingwoai / FairMOT-BDD100K

A fork of FairMOT used to do MOT on BDD100K Dataset
MIT License
27 stars 9 forks source link

showing "If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset." while I train with the pretrained hrnet #11

Open amancodeblast opened 3 years ago

amancodeblast commented 3 years ago

I am using hrnet for this and have mentioned it while training. I downloaded the pretrained network(HRNetV2-W32 official) from link provided by the Official FairMOT repo . I have specified the --arch as 'hrnet'. Can you tell me whats going wrong with loading the pretrained network. Please also provide how to initialize the hrnet from scratch without using any pretrained network that would be really helpful.