The dimensions of the parameters of the trained and tested models do not match

[DanZhang123]

hello:
Since I'm new to this, I have a problem with testing the pascal VOC --> clipart and don,t know where to start:

    While copying the parameter named "RCNN_cls_score.weight", whose dimensions in the model are torch.Size([21, 4224]) and whose dimensions in the checkpoint are torch.Size([21, 4096]).
    While copying the parameter named "RCNN_bbox_pred.weight", whose dimensions in the model are torch.Size([84, 4224]) and whose dimensions in the checkpoint are torch.Size([84, 4096]).

Looking forward to your reply. Thank you very much.

[mrbulb]

@DanZhang123 hello, have you solved this problem?

[ygzhu]

hello, how do you solve this problem?

[ygzhu]

hello, how do you solve this problem?

ok,while you run the script
CUDA_VISIBLE_DEVICES=$GPU_ID python test_net_global_local.py \ --dataset target_dataset --net vgg16 \ --cuda --lc --gc --load_name path_to_model
remove --ls --gc, it will work