vector

try this ``` import torch import mmcv import sys from mmrazor.models.builder import build_algorithm from mmcv.runner import get_dist_info, init_dist, load_checkpoint from mmcls.models import build_classifier def split_student_model(cls_cfg_path, cls_model_path, device='cuda', save_path=None): """ :param:...

> > try this > > ``` > > from mmcv.runner import get_dist_info, init_dist, load_checkpoint > > from mmrazor.models.builder import build_algorithm > > > > def split_student_model(cls_cfg_path, cls_model_path, device='cuda', save_path):...

> Would you like to make a PR? @maxrumi ok, I will make a PR.

> > > > Hi, Thank you for your code. I try your method in classification and segmentation model, both of them can split the student model successfully . BTW,...

you need to write some code to train zico_mnist, and define variable_scope 'net'. After training , put checkpoint under pretrained/mnist_zico_trained