DingXiaoH / RepLKNet-pytorch

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)
MIT License
867 stars 86 forks source link

About seg fine-tuning #33

Open heikeyuhuajia opened 2 years ago

heikeyuhuajia commented 2 years ago

Hello, I want to perform fine-tuning in the split task, but I can't find some_config.py in the command line. Do I need to write it myself?

tthupup commented 2 years ago

Hello, do you also use mmseg? Can we talk about it? My wechat is tametamet

DingXiaoH commented 2 years ago

Hi, in MMSegmentation, a training task is defined by a config file. Here some_config.py refers to any config file we have provided. You need to download the weights of a pretrained backbone model and use the corresponding config file to start the training.