Strange Output #439

Closed
opened 2023-08-01 10:57:45 +02:00 by superbunny38 · 2 comments
superbunny38 commented 2023-08-01 10:57:45 +02:00 (Migrated from github.com)

Hello, thank you for sharing your work :)

I was trying to inference with your model using your given images and video, and the converted video seems very strange. I followed every code in colab, but the result shows as follows:

image

Also, I doubt if this line of warning is a clue for my problem: Pretrained network G has fewer layers; The following are not initialized: ['down0', 'first_layer', 'last_layer', 'up0']

I'll wait for your reply, thank you! :)

Hello, thank you for sharing your work :) I was trying to inference with your model using your given images and video, and the converted video seems very strange. I followed every code in colab, but the result shows as follows: <img width="1025" alt="image" src="https://github.com/neuralchen/SimSwap/assets/48243487/48f9ae55-1978-46e8-ad83-e526300eb097"> Also, I doubt if this line of warning is a clue for my problem: `Pretrained network G has fewer layers; The following are not initialized: ['down0', 'first_layer', 'last_layer', 'up0']` I'll wait for your reply, thank you! :)
ShawnLeung-SII commented 2023-08-06 15:11:05 +02:00 (Migrated from github.com)

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/
@superbunny38

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/ @superbunny38
superbunny38 commented 2023-08-07 07:36:14 +02:00 (Migrated from github.com)

Oh! thank you so much :D

Oh! thank you so much :D
Sign in to join this conversation.