garvit-32/face-recognition-in-presence-of-mask

Face recognition in presence of mask

The task in this project is to match a face image without any occlusion with a face image covered with one of these masking approaches. This repo is a solution of summer challenge given by IITJ.

Demo

Steps to run

1. Clone this repository

git clone https://github.com/Garvit-32/Face-recognition-in-presence-of-Mask.git

2. Install all the dependencies

pip install -r requirements.txt

3. Download and paste the pretrained weight of face detection model in ./face_detection/weights/ using the link
4. Download the hand made dataset using the link ~ 110 MB
5. Extract and paste it in project root directory
6. (optional) You can use your dataset also but it follow a specific structure of directory

-dataset/
	-person_name_1/
		-image_01
		-image_02
	-person_name_2/
		-image_01
		-image_02

7. Run generate_database python file to virtually append mask on person face in database

python generate_database.py

8. Train the model

python train.py

Steps to Test it out

1. Extract face in image using extract_face.py edit test_data_path = "to_your_test_path"

python extract_face.py

2. Test your image

python test.py

face-recognition-in-presence-of-mask's Issues

NameError: name 'get_transforms' is not defined

python train.py

Traceback (most recent call last):
File "train.py", line 20, in
trfm = get_transforms(do_flip=True, flip_vert=True, max_zoom=1.2, max_rotate=20.0, max_lighting=0.4)
NameError: name 'get_transforms' is not defined

The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable.

C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\torch\nn\functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at ..\c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
epoch train_loss valid_loss error_rate accuracy time
C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\torch\nn\functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at ..\c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
epoch train_loss valid_loss error_rate accuracy time
Traceback (most recent call last):
File "", line 1, in
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\spawn.py", line 233, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\spawn.py", line 284, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "D:\iiitdm\RESEARCH\Face-recognition-in-presence-of-Mask-master\Face-recognition-in-presence-of-Mask-master\train.py", line 34, in
learn.fit_one_cycle(6, max_lr =[1e-6, 1e-4, 1e-3])
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\fastai\train.py", line 23, in fit_one_cycle
learn.fit(cyc_len, max_lr, wd=wd, callbacks=callbacks)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\fastai\basic_train.py", line 200, in fit
fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\fastai\basic_train.py", line 99, in fit
for xb,yb in progress_bar(learn.data.train_dl, parent=pbar):
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\fastprogress\fastprogress.py", line 47, in iter
raise e
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\fastprogress\fastprogress.py", line 41, in iter
for i,o in enumerate(self.gen):
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\fastai\basic_data.py", line 75, in iter
for b in self.dl: yield self.proc_batch(b)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\torch\utils\data\dataloader.py", line 359, in iter
return self._get_iterator()
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\site-packages\torch\utils\data\dataloader.py", line 918, in init
w.start()
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\context.py", line 327, in _Popen
return Popen(process_obj)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\spawn.py", line 151, in get_preparation_data
_check_not_importing_main()
File "C:\Users\anjuk\anaconda3_1\envs\face\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if name == 'main':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.