Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Can anyone help? Pretrained network G has fewer layers; The following are not initialized: ['down0', "first_layer',"last_layer','up0‘] #435

Open
GoodFanxinran opened this issue Jul 24, 2023 · 3 comments
Open

Can anyone help? Pretrained network G has fewer layers; The following are not initialized: ['down0', "first_layer',"last_layer','up0‘] #435

GoodFanxinran opened this issue Jul 24, 2023 · 3 comments

Comments

@GoodFanxinran
Copy link

I got the strange image when I ran this:
python test_one_image.py --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/

result

Here is the details:
image

Don`t know the reason.
@neuralchen Could you please give me some suggestions if you are avaliable?
@KleinXin
Copy link

KleinXin commented Jul 24, 2023 •
edited
Loading

me too
many people have reported this problem

#432

#247

@nghiap
Copy link

nghiap commented Jul 29, 2023

Have you got this file ( latestnet_G.pth) in your /checkpoints/people folder? and that it is about 215Mb? It not then your model is not sufficiently trained. You can download the trained model from here: https://github.com/neuralchen/SimSwap/releases,
if you do 224, then download the older one (not 512), and extract it to the folder above.

@shidalao
Copy link

shidalao commented Aug 8, 2023

solved, solution form here

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@KleinXin @nghiap @GoodFanxinran @shidalao