无法从 py-feat 初始化检测器 class 的对象

Question

我尝试根据以下说明从视频中检测 FEX： https://py-feat.org/content/detector.html#detecting-fex-from-videos

但是我无法初始化 Detector class 的对象。我使用的代码：

from feat import Detector

face_model = "retinaface"
landmark_model = "mobilenet"
au_model = "rf"
emotion_model = "resmasknet"
detector = Detector(face_model=face_model, landmark_model=landmark_model, au_model=au_model,
                    emotion_model=emotion_model)

if __name__ == '__main__':
    pass

我收到以下错误：

C:\Users\User\AppData\Roaming\Python\Python39\site-packages\nilearn\input_data\__init__.py:27: FutureWarning: The import path 'nilearn.input_data' is deprecated in version 0.9. Importing from 'nilearn.input_data' will be possible at least until release 0.13.0. Please import from 'nilearn.maskers' instead.
  warnings.warn(message, FutureWarning)
Loading Face Detection model:  retinaface
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\mobilenet0.25_Final.pth
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\mobilenet_224_model_best_gdconv_external.pth.tar
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\hog_pca_all_emotio.joblib
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\hog_pca_all_emotio.joblib
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\hog_scalar_aus.joblib
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\RF_568.joblib
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\hog_pca_all_emotio.joblib
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\hog_scalar_aus.joblib
Using downloaded and verified file: C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\ResMaskNet_Z_resmasking_dropout1_rot30.pth
Loading Face Landmark model:  mobilenet
Loading au model:  rf
Loading emotion model:  resmasknet
Traceback (most recent call last):
  File "C:\Users\User\Desktop\DetectFEXFromVideos\main.py", line 7, in <module>
    detector = Detector(face_model=face_model, landmark_model=landmark_model, au_model=au_model,
  File "C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\detector.py", line 227, in __init__
    self.emotion_model = ResMaskNet()
  File "C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\emo_detectors\ResMaskNet\resmasknet_test.py", line 748, in __init__
    torch.load(
  File "C:\Users\User\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 713, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "C:\Users\User\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 938, in _legacy_load
    typed_storage._storage._set_from_file(
RuntimeError: unexpected EOF, expected 32606425 more bytes. The file might be corrupted.

Process finished with exit code 1

我是 Python 的新手，这就是为什么我没有更改对象初始化中的任何参数的原因。没看懂分别是什么意思

P.S。也许有人知道，如何解决前 2 行的问题？

Answer 1

您的某个文件似乎已损坏。

您可以尝试打开目录C:\Users\User\AppData\Roaming\Python\Python39\site-packages\feat\resources\解决问题并删除文件 ResMaskNet_Z_resmasking_dropout1_rot30.pth.

然后运行再次输入代码，它应该会重新下载已删除的文件。

前两行的警告只是一个警告，它表示库 nilearn 中的某些代码已被弃用。大多数时候你会忽略这一行，这可能会在未来的补丁中被 nilearn 的编码人员修复。

无法从 py-feat 初始化检测器 class 的对象

Can't initialize object of Detector class from py-feat

python

artificial-intelligence

python-3.x