neuralchen / SimSwap

An arbitrary face-swapping framework on images and videos with one single trained model!

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

New Issue about:Pretrained network G has fewer layers

Xiujian-LIANG opened this issue · comments

Totally follow the guidance of this method. And I am sure that the pretrain models are downloaded from the link given by SimSwap.
But the Error is:
Pretrained network G has fewer layers; The following are not initialized:
['down0', 'first_layer', 'last_layer', 'up0']
I see that many same issues here, looking forward to your reply. Thanks.

I solved that. The first test file lack a hyperparameters. Just add the --crop_size 224/512 after py command. Such as
python test_one_image.py --crop_size 224 --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/