code:
paper:
论文
介绍
方法
实验
结论
复现
Image generation
问题1:No models "dcface/dcface/pretrained_models/adaface_ir101_webface4m.ckpt'
Traceback (most recent call last):File "/data/dcface/dcface/src/recognition/recognition_helper.py", line 53, in download_ir_pretrained_statedictsubprocess.check_call([os.path.expanduser('/opt/conda/envs/dcface/lib/python3.7/site-packages/gdown'), '--id', _id])File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 358, in check_callretcode = call(*popenargs, **kwargs)File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 339, in callwith Popen(*popenargs, **kwargs) as p:File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 800, in __init__restore_signals, start_new_session)File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 1551, in _execute_childraise child_exception_type(errno_num, err_msg, err_filename)
PermissionError: [Errno 13] Permission denied: '/opt/conda/envs/dcface/lib/python3.7/site-packages/gdown'During handling of the above exception, another exception occurred:Traceback (most recent call last):File "synthesis.py", line 140, in <module>main()File "synthesis.py", line 77, in mainpl_module: LightningModule = hydra.utils.instantiate(model_hparam)()File "/data/dcface/dcface/src/trainer.py", line 57, in __init__self.recognition_model_eval: RecognitionModel = make_recognition_model(self.hparams.recognition_eval)File "/data/dcface/dcface/src/recognition/recognition_helper.py", line 264, in make_recognition_modelmodel_statedict = download_ir_pretrained_statedict(backbone_name, 'webface4m', 'adaface')File "/data/dcface/dcface/src/recognition/recognition_helper.py", line 56, in download_ir_pretrained_statedictsubprocess.check_call([os.path.expanduser('/opt/conda/envs/dcface/lib/python3.7/site-packages/gdown'), '--id', _id])File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 358, in check_callretcode = call(*popenargs, **kwargs)File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 339, in callwith Popen(*popenargs, **kwargs) as p:File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 800, in __init__restore_signals, start_new_session)File "/opt/conda/envs/dcface/lib/python3.7/subprocess.py", line 1551, in _execute_childraise child_exception_type(errno_num, err_msg, err_filename)
PermissionError: [Errno 13] Permission denied: '/opt/conda/envs/dcface/lib/python3.7/site-packages/gdown'
报错没直接报缺少文件,而是一个包gdown的问题,解决的方向就错了,print了一下发现是因为checkpoint_path的文件缺失,发现缺失的权重作者没给出,搜索后在作者的另一个项目里找到了:
参考:mk-minchul/AdaFace (github.com)
Google 云端硬盘 - 病毒扫描警告
id_image:
style_image:
generated_images:
generate dataset
Training generator
Training Face Recognition Model
to be released
dcface datasets:https://github.com/mk-minchul/dcface?tab=readme-ov-file#dataset-release