search

mantasu / glasses-detector

Glasses detection, classification and segmentation
https://mantasu.github.io/glasses-detector/
MIT License
39 stars 6 forks source link

Could you help me? #10

Closed ale-trevizoli closed 4 months ago

ale-trevizoli commented 5 months ago

Hi! I'm trying to use, I tried first to clone this source code, but I'm using Py 3.11 and I receive a lot of errors, so now I'm using pip install glasses-detector (compiled package).

but I'm not haven error codes that I had when I use src code, but I think it's not finding something that need to download.

Thanks! I'm searching for an glasses detector for long time, hope to can use this.

glasses-detector -i .\fotos\foto_alexandre.jpg --kind anyglasses-classifier Downloading: "https://github.com/mantasu/glasses-detector/releases/download/eyeglasses_classifier_shufflenet_v2_x0_5.pth" to C:\Users\Alexandre/.cache\torch\hub\checkpoints\eyeglasses_classifier_shufflenet_v2_x0_5.pth Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "C:\Program Files\Python311\Scripts\glasses-detector.exe__main.py", line 7, in File "C:\Program Files\Python311\Lib\site-packages\glasses_detector__main.py", line 175, in main model = model_cls(base_model=base_model, pretrained=True).to(device).eval() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\site-packages\glasses_detector\classifiers.py", line 195, in init__ self.eyeg_classifier = EyeglassesClassifier(base_model[0], pretrained[0]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\site-packages\glasses_detector\classifiers.py", line 73, in init super().init__(base_model, pretrained) File "C:\Program Files\Python311\Lib\site-packages\glasses_detector\bases\base_classifier.py", line 72, in init super().init(*args, *kwargs) File "C:\Program Files\Python311\Lib\site-packages\glasses_detector\bases\base_model.py", line 134, in init self._init_from_base_model(base_model, pretrained) File "C:\Program Files\Python311\Lib\site-packages\glasses_detector\bases\base_model.py", line 265, in _init_from_base_model self._load_weights_from_url(self.kind, self.name, version) File "C:\Program Files\Python311\Lib\site-packages\glasses_detector\bases\base_model.py", line 280, in _load_weights_from_url weights = torch.hub.load_state_dict_from_url(url, map_location=device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\site-packages\torch\hub.py", line 766, in load_state_dict_from_url download_url_to_file(url, cached_file, hash_prefix, progress=progress) File "C:\Program Files\Python311\Lib\site-packages\torch\hub.py", line 620, in download_url_to_file u = urlopen(req) ^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\urllib\request.py", line 216, in urlopen return opener.open(url, data, timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\urllib\request.py", line 525, in open response = meth(req, response) ^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\urllib\request.py", line 634, in http_response response = self.parent.error( ^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\urllib\request.py", line 563, in error return self._call_chain(args) ^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\urllib\request.py", line 496, in _call_chain result = func(*args) ^^^^^^^^^^^ File "C:\Program Files\Python311\Lib\urllib\request.py", line 643, in http_error_default raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 404: Not Found

mantasu commented 5 months ago

Hey, currently only the package installable from pip works, i.e., the latest v0.1.1 release (if you consider cloning, please clone the release). It does not have a model for the eyeglasses classifier, but you can manually download the weights. Check this issue on how to set up the classifier.

In short:

  1. Download eyeglasses_classifier_shufflenet_v2_x0_5.zip and extract
  2. Put eyeglasses_classifier_shufflenet_v2_x0_5.pth inside C:\Users\<Your Username>\.cache\torch\hub\checkpoints
  3. Specify --size small

If you experience further errors, let me know~

The current source code is heavily under development and will have a much better user interface and more features and it should be finished by the end of February (depending on when the models finish training). So please do not clone the repository directly.

ale-trevizoli commented 5 months ago

thanks - your suggestion worked!

is possible to define different folder to put model?

mantasu commented 5 months ago

In this version, it may be a bit tricky as you would need to create a python script and manually load the weights from a custom location when instantiating the model. However, you could also simply change torch hub path, e.g., on windows:

setx TORCH_HOME "C:\torch_models"

Then just place eyeglasses_classifier_shufflenet_v2_x0_5.pth inside C:\torch_models\hub\checkpoints