Right at the start of the use of the library for the first time,
detector = feat.Detector()
breaks the code with the error message added at the end of this message.
I presume the error might be that the code tries to download the necessary pre-trained models listed in the model_list.json file from the repository, but some of the model files are not available. To give an example model files like Logistic_520.joblib and svm_568.joblib do not seem to be in the repository anymore. Very likely, without any parameters given, the code tries to load the pre-trained "svm" (as the default "au_detector"), and breaks as the svm_568.joblib file could not be found in the repository.
The error message mentioned is as follows:
Traceback (most recent call last):
File ".....\Programs\Python\Python39\lib\code.py", line 90, in runcode
exec(code, self.locals)
File "", line 1, in
File ".....\env\lib\site-packages\feat\detector.py", line 108, in init
face, landmark, au, emotion, facepose = get_pretrained_models(
File ".....\env\lib\site-packages\feat\pretrained.py", line 239, in get_pretrained_models
download_url(url, get_resource_path(), verbose=verbose)
File ".....\env\lib\site-packages\feat\utils.py", line 1066, in download_url
return tv_download_url(*args, **kwargs)
File ".....\env\lib\site-packages\torchvision\datasets\utils.py", line 131, in download_url
url = _get_redirect_url(url, max_hops=max_redirect_hops)
File ".....\env\lib\site-packages\torchvision\datasets\utils.py", line 79, in _get_redirect_url
with urllib.request.urlopen(urllib.request.Request(url, headers=headers)) as response:
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 214, in urlopen
return opener.open(url, data, timeout)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 523, in open
response = meth(req, response)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 632, in http_response
response = self.parent.error(
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 555, in error
result = self._call_chain(*args)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 494, in _call_chain
result = func(*args)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 747, in http_error_302
return self.parent.open(new, timeout=req.timeout)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 523, in open
response = meth(req, response)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 632, in http_response
response = self.parent.error(
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 561, in error
return self._call_chain(*args)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 494, in _call_chain
result = func(*args)
File ".....\AppData\Local\Programs\Python\Python39\lib\urllib\request.py", line 641, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found
Right at the start of the use of the library for the first time,
detector = feat.Detector()breaks the code with the error message added at the end of this message.
I presume the error might be that the code tries to download the necessary pre-trained models listed in the model_list.json file from the repository, but some of the model files are not available. To give an example model files like Logistic_520.joblib and svm_568.joblib do not seem to be in the repository anymore. Very likely, without any parameters given, the code tries to load the pre-trained "svm" (as the default "au_detector"), and breaks as the svm_568.joblib file could not be found in the repository.
The error message mentioned is as follows: