Skip to main content

An easy to use face detection module based on MTCNN and RetinaFace algorithms.

Project description

FDet-Offline: just like FDet, but offline

Download like this:

pip install fdet-offline --find-links https://download.pytorch.org/whl/torch_stable.html

Package depends on torch-packages not in PyPi.


A version of fdet where you don't have to access the internet to download the weights.

These are the changes:

MTCNN (only works for this model at the moment)

1.

In fdet/mtcnn.py, line 73-76, the url for the MTCNN-weights are listed:

base_url = 'https://github.com/acnazarejr/fdet/releases/download/weights/'
self._pnet = self.__load_model(_PNet, base_url + 'mtcnn_pnet.pt')
self._rnet = self.__load_model(_RNet, base_url + 'mtcnn_rnet.pt')
self._onet = self.__load_model(_ONet, base_url + 'mtcnn_onet.pt')

I downloaded those weights and created packages to import them (because PyPi has a 100MB max on package size, this was the solution).

I put the weights in the directory weights in the package fdet_offline_mtcnn_weights. The function fdet_offline_mtcnn_weights.import_weights takes mtcnn_type as input and returns a partial function of torch.load.

This partial function gets map_location from __load_model.

The previously mentioned fdet/mtcnn.py, line 73-76, now looks like this:

self._pnet = self.__load_model(_PNet, 'pnet')
self._rnet = self.__load_model(_RNet, 'rnet')
self._onet = self.__load_model(_ONet, 'onet')

In fdet/mtcnn.py, what previously was (url was input):

def __load_model(self, net_class: type, url: str) -> torch.nn.Module:
    """Download and construct the models"""
    try:
        state_dict = load_state_dict_from_url(url, map_location=self._device_control)

is now (mtcnn_type is input):

def __load_model(self, net_class: type, mtcnn_type: str) -> torch.nn.Module:
    """Download and construct the models"""
    try:
        load_state_dict = import_weights.load_partial(mtcnn_type)
        state_dict = load_state_dict(map_location=self._device_control)

2.

At fdet/mtcnn.py, line 427:

state_dict = load_state_dict_from_url(url, map_location=self._device_control)

load_state_dict_from_url, returns a torch.load which takes the weight-file as input. I replaced the load_state_dict_from_url with torch.load, and that's it.

That line now states this instead;

state_dict = torch.load(url, map_location=self._device_control)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fdet-offline-1.0.5.tar.gz (21.7 kB view details)

Uploaded Source

Built Distribution

fdet_offline-1.0.5-py3-none-any.whl (23.3 kB view details)

Uploaded Python 3

File details

Details for the file fdet-offline-1.0.5.tar.gz.

File metadata

  • Download URL: fdet-offline-1.0.5.tar.gz
  • Upload date:
  • Size: 21.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.0 requests/2.22.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.8.5

File hashes

Hashes for fdet-offline-1.0.5.tar.gz
Algorithm Hash digest
SHA256 62947fd7479c723bb8669c26d8b42b77d103cc057b0bec757dbdd12accf056ad
MD5 99a7cab39c07ae8272055bfa5689d75a
BLAKE2b-256 3b76d00964e62e96407452fcdf50d3a957a275bc8a2f92fe2f66905b4a6f5197

See more details on using hashes here.

File details

Details for the file fdet_offline-1.0.5-py3-none-any.whl.

File metadata

  • Download URL: fdet_offline-1.0.5-py3-none-any.whl
  • Upload date:
  • Size: 23.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.0 requests/2.22.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.8.5

File hashes

Hashes for fdet_offline-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 323f62d00c0ff9e28a43cd4423794286779df189474f2dd169923f689bcf3562
MD5 01fc12d4335bdbb632907878b30dba7c
BLAKE2b-256 27e27447aa1c885a8daf277a221df0b708ab7cd68e5331f34714c59f7f2620d7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page