在转变参数之后

[yeqingmei123]

为什么会出现新的问题呢
swap_layer = 10
Traceback (most recent call last):
File "demo/quick_try.py", line 253, in
main()
File "demo/quick_try.py", line 242, in main
style_image = testor.run(args.img_path, args.style, args.swap_layer)
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/grad_mode.py", line 15, in decorate_context
return func(*args, **kwargs)
File "demo/quick_try.py", line 212, in run
if swap_layer > 0 else _swap_layer[style])
File "demo/quick_try.py", line 192, in layerSwap
randomize_noise=False)
File "/content/MMGEN-FaceStylor/MMGEN-FaceStylor/agilegan/architectures/ADAStyleGAN2/generator_discriminator.py", line 200, in swap_forward
return img, save_swap_layer
UnboundLocalError: local variable 'save_swap_layer' referenced before assignment

这是什么问题啊

[mm-assistant]

Please use English or English & Chinese for issues so that we could have broader discussion.

[yeqingmei123]

在改变参数之后，
为什么运行结果会报上面的错呀

[yeqingmei123]

when ichange the" swap_layer = 10", in the colab, there are some errors showing ,like
Traceback (most recent call last):
File "demo/quick_try.py", line 253, in
main()
File "demo/quick_try.py", line 242, in main
style_image = testor.run(args.img_path, args.style, args.swap_layer)
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/grad_mode.py", line 15, in decorate_context
return func(*args, **kwargs)
File "demo/quick_try.py", line 212, in run
if swap_layer > 0 else _swap_layer[style])
File "demo/quick_try.py", line 192, in layerSwap
randomize_noise=False)
File "/content/MMGEN-FaceStylor/MMGEN-FaceStylor/agilegan/architectures/ADAStyleGAN2/generator_discriminator.py", line 200, in swap_forward
return img, save_swap_layer
UnboundLocalError: local variable 'save_swap_layer' referenced before assignment
how to fix it!!

[plyfager]

Hi @yeqingmei123, Thx for your interest. swap_layer is not supposed to be larger than 7. You can try a smaller number. I will fix this bug later.

[yeqingmei123]

hello ，i meet another question，when i first to run this sentence，it has a result ,but when i run it again,it has this error,
i can't find a solution ,please give me a help! thx

!python demo/quick_try.py demo/src.png --style toonify --save-path demo/src_output1.png

File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 45, in build_from_cfg
f'{obj_type} is not in the {registry.name} registry')
KeyError: 'ADAStyleGAN2Discriminator is not in the module registry'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "demo/quick_try.py", line 253, in
main()
File "demo/quick_try.py", line 240, in main
transfer_ckpt=os.path.join(args.ckpt_path, transfer_ckpt_name))
File "demo/quick_try.py", line 121, in init
device='cpu').eval()
File "/content/mmgeneration-0.6.0/mmgen/apis/inference.py", line 36, in init_model
config.model, train_cfg=config.train_cfg, test_cfg=config.test_cfg)
File "/content/mmgeneration-0.6.0/mmgen/models/builder.py", line 32, in build_model
return build(cfg, MODELS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
File "/content/mmgeneration-0.6.0/mmgen/models/builder.py", line 27, in build
return build_from_cfg(cfg, registry, default_args)
File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 55, in build_from_cfg
raise type(e)(f'{obj_cls.name}: {e}')
KeyError: "PSPTransfer: 'ADAStyleGAN2Discriminator is not in the module registry'"

[chy0315]

你好，我遇到另外一个问题，第一次运行这句话的时候，有一个结果，但是当我再次运行的时候，出现了这个错误， 我找不到解决办法，请帮助我！谢谢

!python demo/quick_try.py demo/src.png --style toonify --save-path demo/src_output1.png

文件“/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py”，第 45 行，在 build_from_cfg f'{obj_type} 不在 {registry.name} 注册表中'） KeyError： 'ADAStyleGAN2Discriminator is not in the module registry' 在处理上述异常的过程中，发生了另一个异常： Traceback（最近调用最后一次）： 文件“demo/quick_try.py”，第 253 行，在 main() 文件“demo/quick_try.py”中。 py", line 240, in main transfer_ckpt=os.path.join(args.ckpt_path, transfer_ckpt_name)) File "demo/quick_try.py", line 121, in init device='cpu').eval() File "/ content/mmgeneration-0.6.0/mmgen/apis/inference.py”，第 36 行，在 init_model 中 config.model, train_cfg=config.train_cfg, test_cfg=config.test_cfg) 文件“/content/mmgeneration-0.6.0/mmgen/models/builder.py”, line 32, in build_model return build(cfg, MODELS, dict( train_cfg=train_cfg, test_cfg=test_cfg)) 文件“/content/mmgeneration-0.6.0/mmgen/models/builder.py”，第 27 行，在构建 返回 build_from_cfg(cfg, registry, default_args) 文件“/usr/local/ lib/python3.7/dist-packages/mmcv/utils/registry.py”，第 55 行，在 build_from_cfg 中 raise type(e)(f'{obj_cls.name } : {e}') KeyError: “PSPTransfer: 'ADAStyleGAN2Discriminator不在模块注册表中'”

Have you solved it? I also encountered the same problem.