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

New Issue

2023-07-24T11:49:27+02:00

GoodFanxinran commented

2023-07-24 11:49:27 +02:00

(Migrated from github.com)

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/

Here is the details:

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

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](https://github.com/neuralchen/SimSwap/assets/104200736/3f40e76c-a998-4892-a909-7b2373584333) Here is the details: <img width="541" alt="image" src="https://github.com/neuralchen/SimSwap/assets/104200736/fd60a6ca-84ed-4c7c-b389-db50f7c910fa"> Don`t know the reason. @neuralchen Could you please give me some suggestions if you are avaliable?

KleinXin commented

2023-07-24 15:05:41 +02:00

(Migrated from github.com)

me too
many people have reported this problem

https://github.com/neuralchen/SimSwap/issues/432

https://github.com/neuralchen/SimSwap/issues/247

me too many people have reported this problem https://github.com/neuralchen/SimSwap/issues/432 https://github.com/neuralchen/SimSwap/issues/247

nghiap commented

2023-07-30 00:11:58 +02:00

(Migrated from github.com)

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.

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 commented

2023-08-08 11:02:51 +02:00

(Migrated from github.com)

solved, solution form here

solved, solution form [here](https://github.com/neuralchen/SimSwap/issues/432#issuecomment-1666855648)

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#435