diff options
Diffstat (limited to 'megapixels/app')
| -rw-r--r-- | megapixels/app/models/bbox.py | 6 | ||||
| -rw-r--r-- | megapixels/app/processors/face_detector.py | 48 | ||||
| -rw-r--r-- | megapixels/app/processors/face_pose.py | 148 | ||||
| -rw-r--r-- | megapixels/app/processors/face_recognition.py | 29 | ||||
| -rw-r--r-- | megapixels/app/settings/app_cfg.py | 7 | ||||
| -rw-r--r-- | megapixels/app/settings/paths.py | 163 | ||||
| -rw-r--r-- | megapixels/app/settings/types.py | 12 |
7 files changed, 302 insertions, 111 deletions
diff --git a/megapixels/app/models/bbox.py b/megapixels/app/models/bbox.py index e6da960e..55a92512 100644 --- a/megapixels/app/models/bbox.py +++ b/megapixels/app/models/bbox.py @@ -262,6 +262,12 @@ class BBox: rect = cls.normalize(cls, rect, dim) return cls(*rect) + def __str__(self): + return f'BBox: ({self._x1},{self._y1}), ({self._x2}, {self._y2}), width:{self._width}, height:{self._height}' + + def __repr__(self): + return f'BBox: ({self._x1},{self._y1}), ({self._x2}, {self._y2}), width:{self._width}, height:{self._height}' + def str(self): """Return BBox as a string "x1, y1, x2, y2" """ return self.as_box() diff --git a/megapixels/app/processors/face_detector.py b/megapixels/app/processors/face_detector.py index 593e9feb..3a90c557 100644 --- a/megapixels/app/processors/face_detector.py +++ b/megapixels/app/processors/face_detector.py @@ -24,15 +24,15 @@ class DetectorMTCNN: from mtcnn.mtcnn import MTCNN self.detector = MTCNN() - def detect(self, im, opt_size=(400,400), opt_conf_thresh=None, opt_pyramids=None, opt_largest=False): + def detect(self, im, size=(400,400), conf_thresh=None, pyramids=None, largest=False): '''Detects face using MTCNN and returns (list) of BBox :param im: (numpy.ndarray) image :returns list of BBox ''' bboxes = [] - #conf_thresh = self.conf_thresh if opt_conf_thresh is None else opt_conf_thresh - #pyramids = self.pyramids if opt_pyramids is None else opt_pyramids - dnn_size = self.dnn_size if opt_size is None else opt_size + #conf_thresh = self.conf_thresh if conf_thresh is None else conf_thresh + #pyramids = self.pyramids if pyramids is None else pyramids + dnn_size = self.dnn_size if size is None else size im = im_utils.resize(im, width=dnn_size[0], height=dnn_size[1]) dim = im.shape[:2][::-1] @@ -43,7 +43,7 @@ class DetectorMTCNN: bbox = BBox.from_xywh_dim(*rect, dim) bboxes.append(bbox) - if opt_largest and len(bboxes) > 1: + if largest and len(bboxes) > 1: # only keep largest bboxes.sort(key=operator.attrgetter('area'), reverse=True) bboxes = [bboxes[0]] @@ -70,34 +70,33 @@ class DetectorDLIBCNN: pyramids = 0 conf_thresh = 0.85 - def __init__(self, opt_gpu=0): + def __init__(self, gpu=0): import dlib self.log = logger_utils.Logger.getLogger() cuda_visible_devices = os.getenv('CUDA_VISIBLE_DEVICES', '') - os.environ['CUDA_VISIBLE_DEVICES'] = str(opt_gpu) + os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu) self.log.info('load model: {}'.format(cfg.DIR_MODELS_DLIB_CNN)) self.detector = dlib.cnn_face_detection_model_v1(cfg.DIR_MODELS_DLIB_CNN) os.environ['CUDA_VISIBLE_DEVICES'] = cuda_visible_devices # reset - def detect(self, im, opt_size=None, opt_conf_thresh=None, opt_pyramids=None, opt_largest=False): + def detect(self, im, size=None, conf_thresh=None, pyramids=None, largest=False): bboxes = [] - conf_thresh = self.conf_thresh if opt_conf_thresh is None else opt_conf_thresh - pyramids = self.pyramids if opt_pyramids is None else opt_pyramids - dnn_size = self.dnn_size if opt_size is None else opt_size + conf_thresh = self.conf_thresh if conf_thresh is None else conf_thresh + pyramids = self.pyramids if pyramids is None else pyramids + dnn_size = self.dnn_size if size is None else size # resize image im = im_utils.resize(im, width=dnn_size[0], height=dnn_size[1]) dim = im.shape[:2][::-1] im = im_utils.bgr2rgb(im) # convert to RGB for dlib # run detector - mmod_rects = self.detector(im, opt_pyramids) + mmod_rects = self.detector(im, pyramids) # sort results for mmod_rect in mmod_rects: - self.log.debug('conf: {}, this: {}'.format(conf_thresh, mmod_rect.confidence)) if mmod_rect.confidence > conf_thresh: bbox = BBox.from_dlib_dim(mmod_rect.rect, dim) bboxes.append(bbox) - if opt_largest and len(bboxes) > 1: + if largest and len(bboxes) > 1: # only keep largest bboxes.sort(key=operator.attrgetter('area'), reverse=True) bboxes = [bboxes[0]] @@ -116,25 +115,24 @@ class DetectorDLIBHOG: self.log = logger_utils.Logger.getLogger() self.detector = dlib.get_frontal_face_detector() - def detect(self, im, opt_size=None, opt_conf_thresh=None, opt_pyramids=0, opt_largest=False): - conf_thresh = self.conf_thresh if opt_conf_thresh is None else opt_conf_thresh - dnn_size = self.size if opt_size is None else opt_size - pyramids = self.pyramids if opt_pyramids is None else opt_pyramids + def detect(self, im, size=None, conf_thresh=None, pyramids=0, largest=False): + conf_thresh = self.conf_thresh if conf_thresh is None else conf_thresh + dnn_size = self.size if size is None else size + pyramids = self.pyramids if pyramids is None else pyramids - im = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + im = im_utils.resize(im, width=dnn_size[0], height=dnn_size[1]) dim = im.shape[:2][::-1] im = im_utils.bgr2rgb(im) # ? hog_results = self.detector.run(im, pyramids) bboxes = [] if len(hog_results[0]) > 0: - self.log.debug(hog_results) for rect, score, direction in zip(*hog_results): if score > conf_thresh: bbox = BBox.from_dlib_dim(rect, dim) bboxes.append(bbox) - if opt_largest and len(bboxes) > 1: + if largest and len(bboxes) > 1: # only keep largest bboxes.sort(key=operator.attrgetter('area'), reverse=True) bboxes = [bboxes[0]] @@ -157,10 +155,10 @@ class DetectorCVDNN: self.net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV) self.net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU) - def detect(self, im, opt_size=None, opt_conf_thresh=None, opt_largest=False, opt_pyramids=None): + def detect(self, im, size=None, conf_thresh=None, largest=False, pyramids=None): """Detects faces and returns (list) of (BBox)""" - conf_thresh = self.conf_thresh if opt_conf_thresh is None else opt_conf_thresh - dnn_size = self.size if opt_size is None else opt_size + conf_thresh = self.conf_thresh if conf_thresh is None else conf_thresh + dnn_size = self.size if size is None else size im = cv.resize(im, dnn_size) blob = cv.dnn.blobFromImage(im, self.dnn_scale, dnn_size, self.dnn_mean) self.net.setInput(blob) @@ -173,7 +171,7 @@ class DetectorCVDNN: rect_norm = net_outputs[0, 0, i, 3:7] bboxes.append(BBox(*rect_norm)) - if opt_largest and len(bboxes) > 1: + if largest and len(bboxes) > 1: # only keep largest bboxes.sort(key=operator.attrgetter('area'), reverse=True) bboxes = [bboxes[0]] diff --git a/megapixels/app/processors/face_pose.py b/megapixels/app/processors/face_pose.py index 67ac685d..f2548b32 100644 --- a/megapixels/app/processors/face_pose.py +++ b/megapixels/app/processors/face_pose.py @@ -22,89 +22,83 @@ class FacePoseDLIB: def __init__(self): pass - def pose(self, landmarks, dim): - '''Calculates pose - ''' - degrees = compute_pose_degrees(landmarks, dim) - return degrees + def pose(self, landmarks, dim, project_points=False): + # computes pose using 6 / 68 points from dlib face landmarks + # based on learnopencv.com and + # https://github.com/jerryhouuu/Face-Yaw-Roll-Pitch-from-Pose-Estimation-using-OpenCV/ + # NB: not as accurate as MTCNN, see @jerryhouuu for ideas + + pose_points_idx = (30, 8, 36, 45, 48, 54) + axis = np.float32([[500,0,0], [0,500,0], [0,0,500]]) + + # 3D model points. + model_points = np.array([ + (0.0, 0.0, 0.0), # Nose tip + (0.0, -330.0, -65.0), # Chin + (-225.0, 170.0, -135.0), # Left eye left corner + (225.0, 170.0, -135.0), # Right eye right corne + (-150.0, -150.0, -125.0), # Left Mouth corner + (150.0, -150.0, -125.0) # Right mouth corner + ]) + + # Assuming no lens distortion + dist_coeffs = np.zeros((4,1)) -# ----------------------------------------------------------- -# utilities -# ----------------------------------------------------------- + # find 6 pose points + pose_points = [] + for j, idx in enumerate(pose_points_idx): + pt = landmarks[idx] + pose_points.append((pt[0], pt[1])) + pose_points = np.array(pose_points, dtype='double') # convert to double + + # create camera matrix + focal_length = dim[0] + center = (dim[0]/2, dim[1]/2) + cam_mat = np.array( + [[focal_length, 0, center[0]], + [0, focal_length, center[1]], + [0, 1, 1]], dtype = "double") + + # solve PnP for rotation and translation + (success, rot_vec, tran_vec) = cv.solvePnP(model_points, pose_points, + cam_mat, dist_coeffs, + flags=cv.SOLVEPNP_ITERATIVE) -def compute_pose_degrees(landmarks, dim): - # computes pose using 6 / 68 points from dlib face landmarks - # based on learnopencv.com and - # https://github.com/jerryhouuu/Face-Yaw-Roll-Pitch-from-Pose-Estimation-using-OpenCV/ - # NB: not as accurate as MTCNN, see @jerryhouuu for ideas - - pose_points_idx = (30, 8, 36, 45, 48, 54) - axis = np.float32([[500,0,0], [0,500,0], [0,0,500]]) - - # 3D model points. - model_points = np.array([ - (0.0, 0.0, 0.0), # Nose tip - (0.0, -330.0, -65.0), # Chin - (-225.0, 170.0, -135.0), # Left eye left corner - (225.0, 170.0, -135.0), # Right eye right corne - (-150.0, -150.0, -125.0), # Left Mouth corner - (150.0, -150.0, -125.0) # Right mouth corner - ]) - - # Assuming no lens distortion - dist_coeffs = np.zeros((4,1)) + result = {} - # find 6 pose points - pose_points = [] - for j, idx in enumerate(pose_points_idx): - pt = landmarks[idx] - pose_points.append((pt[0], pt[1])) - pose_points = np.array(pose_points, dtype='double') # convert to double - - # create camera matrix - focal_length = dim[0] - center = (dim[0]/2, dim[1]/2) - cam_mat = np.array( - [[focal_length, 0, center[0]], - [0, focal_length, center[1]], - [0, 1, 1]], dtype = "double") - - # solve PnP for rotation and translation - (success, rot_vec, tran_vec) = cv.solvePnP(model_points, pose_points, - cam_mat, dist_coeffs, - flags=cv.SOLVEPNP_ITERATIVE) + # project points + if project_points: + pts_im, jac = cv.projectPoints(axis, rot_vec, tran_vec, cam_mat, dist_coeffs) + pts_model, jac2 = cv.projectPoints(model_points, rot_vec, tran_vec, cam_mat, dist_coeffs) + result['points_model'] = pts_model + result['points_image'] = pts_im + result['point_nose'] = tuple(landmarks[pose_points_idx[0]]) - # project points - #pts_im, jac = cv.projectPoints(axis, rot_vec, tran_vec, cam_mat, dist_coeffs) - #pts_model, jac2 = cv.projectPoints(model_points, rot_vec, tran_vec, cam_mat, dist_coeffs) - rvec_matrix = cv.Rodrigues(rot_vec)[0] - - # convert to degrees - proj_matrix = np.hstack((rvec_matrix, tran_vec)) - eulerAngles = cv.decomposeProjectionMatrix(proj_matrix)[6] - pitch, yaw, roll = [math.radians(x) for x in eulerAngles] - pitch = math.degrees(math.asin(math.sin(pitch))) - roll = -math.degrees(math.asin(math.sin(roll))) - yaw = math.degrees(math.asin(math.sin(yaw))) - degrees = {'pitch': pitch, 'roll': roll, 'yaw': yaw} - - # add nose point - #pt_nose = tuple(landmarks[pose_points_idx[0]]) - return degrees - #return pts_im, pts_model, degrees, pt_nose + rvec_matrix = cv.Rodrigues(rot_vec)[0] + + # convert to degrees + proj_matrix = np.hstack((rvec_matrix, tran_vec)) + eulerAngles = cv.decomposeProjectionMatrix(proj_matrix)[6] + pitch, yaw, roll = [math.radians(x) for x in eulerAngles] + pitch = math.degrees(math.asin(math.sin(pitch))) + roll = -math.degrees(math.asin(math.sin(roll))) + yaw = math.degrees(math.asin(math.sin(yaw))) + degrees = {'pitch': pitch, 'roll': roll, 'yaw': yaw} + result['degrees'] = degrees + return result -def draw_pose(im, pts_im, pts_model, pt_nose): - cv.line(im, pt_nose, tuple(pts_im[1].ravel()), (0,255,0), 3) #GREEN - cv.line(im, pt_nose, tuple(pts_im[0].ravel()), (255,0,), 3) #BLUE - cv.line(im, pt_nose, tuple(pts_im[2].ravel()), (0,0,255), 3) #RED - return im + def draw_pose(self, im, pts_im, pts_model, pt_nose): + cv.line(im, pt_nose, tuple(pts_im[1].ravel()), (0,255,0), 3) #GREEN + cv.line(im, pt_nose, tuple(pts_im[0].ravel()), (255,0,), 3) #BLUE + cv.line(im, pt_nose, tuple(pts_im[2].ravel()), (0,0,255), 3) #RED -def draw_degrees(im, degrees, color=(0,255,0)): - for i, item in enumerate(degrees.items()): - k, v = item - t = '{}: {:.2f}'.format(k, v) - origin = (10, 30 + (25 * i)) - cv.putText(im, t, origin, cv.FONT_HERSHEY_SIMPLEX, 0.5, color, thickness=2, lineType=2)
\ No newline at end of file + + def draw_degrees(self, im, degrees, color=(0,255,0)): + for i, item in enumerate(degrees.items()): + k, v = item + t = '{}: {:.2f}'.format(k, v) + origin = (10, 30 + (25 * i)) + cv.putText(im, t, origin, cv.FONT_HERSHEY_SIMPLEX, 0.5, color, thickness=2, lineType=2)
\ No newline at end of file diff --git a/megapixels/app/processors/face_recognition.py b/megapixels/app/processors/face_recognition.py index 9c3a301d..e0b9f752 100644 --- a/megapixels/app/processors/face_recognition.py +++ b/megapixels/app/processors/face_recognition.py @@ -17,25 +17,38 @@ class RecognitionDLIB: # https://github.com/davisking/dlib/blob/master/python_examples/face_recognition.py # facerec.compute_face_descriptor(img, shape, 100, 0.25) - def __init__(self, opt_gpu=0): + def __init__(self, gpu=0): self.log = logger_utils.Logger.getLogger() - if opt_gpu > 0: + + if gpu > -1: cuda_visible_devices = os.getenv('CUDA_VISIBLE_DEVICES', '') - os.environ['CUDA_VISIBLE_DEVICES'] = str(opt_gpu) - self.predictor = dlib.shape_predictor(cfg.DIR_MODELS_DLIB_5PT) - self.facerec = dlib.face_recognition_model_v1(cfg.DIR_MODELS_DLIB_FACEREC_RESNET) + os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu) + + self.predictor = dlib.shape_predictor(cfg.DIR_MODELS_DLIB_5PT) + self.facerec = dlib.face_recognition_model_v1(cfg.DIR_MODELS_DLIB_FACEREC_RESNET) + + if gpu > -1: os.environ['CUDA_VISIBLE_DEVICES'] = cuda_visible_devices # reset GPU env + def vec(self, im, bbox, width=100, - jitters=cfg.DLIB_FACEREC_JITTERS, padding=cfg.DLIB_FACEREC_PADDING): + jitters=cfg.DLIB_FACEREC_JITTERS, padding=cfg.DLIB_FACEREC_PADDING): # Converts image and bbox into 128d vector # scale the image so the face is always 100x100 pixels + #self.log.debug('compute scale') scale = width / bbox.width - im = cv.resize(im, (scale, scale), interploation=cv.INTER_LANCZOS4) + #im = cv.resize(im, (scale, scale), cv.INTER_LANCZOS4) + #self.log.debug('resize') + cv.resize(im, None, fx=scale, fy=scale, interpolation=cv.INTER_LANCZOS4) + #self.log.debug('to dlib') bbox_dlib = bbox.to_dlib() + #self.log.debug('precitor') face_shape = self.predictor(im, bbox_dlib) - vec = self.facerec.compute_face_descriptor(im, face_shape, jitters, padding) + # vec = self.facerec.compute_face_descriptor(im, face_shape, jitters, padding) + #self.log.debug('vec') + vec = self.facerec.compute_face_descriptor(im, face_shape, jitters) + #vec = self.facerec.compute_face_descriptor(im, face_shape) return vec diff --git a/megapixels/app/settings/app_cfg.py b/megapixels/app/settings/app_cfg.py index 51392bcc..0507366f 100644 --- a/megapixels/app/settings/app_cfg.py +++ b/megapixels/app/settings/app_cfg.py @@ -9,6 +9,10 @@ import cv2 as cv from app.settings import types from app.utils import click_utils +# ----------------------------------------------------------------------------- +# Metadata type names +# ----------------------------------------------------------------------------- + # ----------------------------------------------------------------------------- # Enun lists used for custom Click Params @@ -17,6 +21,8 @@ from app.utils import click_utils FaceDetectNetVar = click_utils.ParamVar(types.FaceDetectNet) HaarCascadeVar = click_utils.ParamVar(types.HaarCascade) LogLevelVar = click_utils.ParamVar(types.LogLevel) +MetadataVar = click_utils.ParamVar(types.Metadata) +DatasetVar = click_utils.ParamVar(types.Dataset) # # data_store DATA_STORE = '/data_store_hdd/' @@ -24,6 +30,7 @@ DATA_STORE_NAS = '/data_store_nas/' DATA_STORE_HDD = '/data_store_hdd/' DATA_STORE_SSD = '/data_store_ssd/' DIR_DATASETS = join(DATA_STORE,'datasets') +DIR_DATSET_NAS = join(DIR_DATASETS, 'people') DIR_APPS = join(DATA_STORE,'apps') DIR_APP = join(DIR_APPS,'megapixels') DIR_MODELS = join(DIR_APP,'models') diff --git a/megapixels/app/settings/paths.py b/megapixels/app/settings/paths.py new file mode 100644 index 00000000..bc1333ba --- /dev/null +++ b/megapixels/app/settings/paths.py @@ -0,0 +1,163 @@ +import os +from os.path import join +import logging + +from vframe.settings import vframe_cfg as vcfg +from vframe.settings import types + +class Paths: + + # class properties + MAPPINGS_DATE = vcfg.SUGARCUBE_DATES[0] + DIR_APP_VFRAME = 'apps/vframe/' + DIR_APP_SA = 'apps/syrianarchive' + DIR_MODELS_VFRAME = join(DIR_APP_VFRAME, 'models') + DIR_DARKNET = join(DIR_MODELS_VFRAME, 'darknet/pjreddie') + DIR_DARKNET_VFRAME = join(DIR_MODELS_VFRAME, 'darknet/vframe') + DIR_MEDIA = join(DIR_APP_SA, 'media') + DIR_METADATA = join(DIR_APP_SA, 'metadata') + DIR_RECORDS = join(DIR_APP_SA, 'records') + DIR_REPORTS = join(DIR_APP_SA, 'reports') + + + def __init__(self): + pass + + @classmethod + def DataStorePath(cls, data_store=types.DataStore.HDD): + return '/data_store_{}'.format(data_store.name.lower()) + + # ------------------------------------------------------------------------------- + # Darknet Paths + + @classmethod + def darknet_classes(cls, data_store=types.DataStore.HDD, opt_net=types.DetectorNet.COCO): + if opt_net == types.DetectorNet.COCO: + fp = join(cls.DIR_DARKNET, 'data', 'coco.names') + elif opt_net == types.DetectorNet.COCO_SPP: + fp = join(cls.DIR_DARKNET, 'data', 'coco.names') + elif opt_net == types.DetectorNet.VOC: + fp = join(cls.DIR_DARKNET, 'data', 'voc.names') + elif opt_net == types.DetectorNet.OPENIMAGES: + fp = join(cls.DIR_DARKNET, 'data', 'openimages.names') + elif opt_net == types.DetectorNet.SUBMUNITION: + fp = join(cls.DIR_DARKNET_VFRAME, 'munitions_09b', 'classes.txt') + return join(cls.DataStorePath(data_store), fp) + + @classmethod + def darknet_data(cls, data_store=types.DataStore.HDD, opt_net=types.DetectorNet.COCO, as_bytes=True): + if opt_net == types.DetectorNet.COCO: + fp = join(cls.DIR_DARKNET, 'cfg', 'coco.data') + elif opt_net == types.DetectorNet.COCO_SPP: + fp = join(cls.DIR_DARKNET, 'cfg', 'coco.data') + elif opt_net == types.DetectorNet.VOC: + fp = join(cls.DIR_DARKNET, 'cfg', 'voc.data') + elif opt_net == types.DetectorNet.OPENIMAGES: + fp = join(cls.DIR_DARKNET, 'cfg', 'openimages.data') + elif opt_net == types.DetectorNet.SUBMUNITION: + fp = join(cls.DIR_DARKNET_VFRAME, 'munitions_09b', 'meta.data') + fp = join(cls.DataStorePath(data_store), fp) + if as_bytes: + return bytes(fp, encoding="utf-8") + else: + return fp + + + @classmethod + def darknet_cfg(cls, data_store=types.DataStore.HDD, opt_net=types.DetectorNet.COCO, as_bytes=True): + if opt_net == types.DetectorNet.COCO: + fp = join(cls.DIR_DARKNET, 'cfg', 'yolov3.cfg') + elif opt_net == types.DetectorNet.COCO_SPP: + fp = join(cls.DIR_DARKNET, 'cfg', 'yolov3-spp.cfg') + elif opt_net == types.DetectorNet.VOC: + fp = join(cls.DIR_DARKNET, 'cfg', 'yolov3-voc.cfg') + elif opt_net == types.DetectorNet.OPENIMAGES: + fp = join(cls.DIR_DARKNET, 'cfg', 'yolov3-openimages.cfg') + elif opt_net == types.DetectorNet.SUBMUNITION: + fp = join(cls.DIR_DARKNET_VFRAME, 'munitions_09b', 'yolov3.cfg') + fp = join(cls.DataStorePath(data_store), fp) + if as_bytes: + return bytes(fp, encoding="utf-8") + else: + return fp + + @classmethod + def darknet_weights(cls, data_store=types.DataStore.HDD, opt_net=types.DetectorNet.COCO, as_bytes=True): + if opt_net == types.DetectorNet.COCO: + fp = join(cls.DIR_DARKNET, 'weights', 'yolov3.weights') + elif opt_net == types.DetectorNet.COCO_SPP: + fp = join(cls.DIR_DARKNET, 'weights', 'yolov3-spp.weights') + elif opt_net == types.DetectorNet.VOC: + fp = join(cls.DIR_DARKNET, 'weights', 'yolov3-voc.weights') + elif opt_net == types.DetectorNet.OPENIMAGES: + fp = join(cls.DIR_DARKNET, 'weights', 'yolov3-openimages.weights') + elif opt_net == types.DetectorNet.SUBMUNITION: + fp = join(cls.DIR_DARKNET_VFRAME, 'munitions_09b/weights', 'yolov3_40000.weights') + fp = join(cls.DataStorePath(data_store), fp) + if as_bytes: + return bytes(fp, encoding="utf-8") + else: + return fp + + # ------------------------------------------------------------------------------- + # Metadata Paths + + @classmethod + def mapping_index(cls, opt_date, data_store=types.DataStore.HDD, verified=types.Verified.VERIFIED, + file_format=types.FileExt.PKL): + """Returns filepath to a mapping file. Mapping files are the original Suguarcube mapping data""" + fname = 'index.pkl' if file_format == types.FileExt.PKL else 'index.json' + # data_store = 'data_store_{}'.format(data_store.name.lower()) + date_str = opt_date.name.lower() + fp = join(cls.DataStorePath(data_store), cls.DIR_METADATA, 'mapping', date_str, verified.name.lower(), fname) + return fp + + @classmethod + def media_record_index(cls, data_store=types.DataStore.HDD, verified=types.Verified.VERIFIED, + file_format=types.FileExt.PKL): + """Returns filepath to a mapping file. Mapping files are the original Suguarcube mapping data""" + fname = 'index.pkl' if file_format == types.FileExt.PKL else 'index.json' + metadata_type = types.Metadata.MEDIA_RECORD.name.lower() + fp = join(cls.DataStorePath(data_store), cls.DIR_METADATA, metadata_type, verified.name.lower(), fname) + return fp + + @classmethod + def metadata_index(cls, metadata_type, data_store=types.DataStore.HDD, + verified=types.Verified.VERIFIED, file_format=types.FileExt.PKL): + """Uses key from enum to get folder name and construct filepath""" + fname = 'index.pkl' if file_format == types.FileExt.PKL else 'index.json' + fp = join(cls.DataStorePath(data_store), cls.DIR_METADATA, metadata_type.name.lower(), + verified.name.lower(), fname) + return fp + + @classmethod + def metadata_dir(cls, metadata_type, data_store=types.DataStore.HDD, verified=types.Verified.VERIFIED): + """Uses key from enum to get folder name and construct filepath""" + fp = join(cls.DataStorePath(data_store), cls.DIR_METADATA, metadata_type.name.lower(), + verified.name.lower()) + return fp + + @classmethod + def metadata_tree_dir(cls, metadata_type, data_store=types.DataStore.HDD): + """Uses key from enum to get folder name and construct filepath""" + fp = join(cls.DataStorePath(data_store), cls.DIR_METADATA, metadata_type.name.lower()) + return fp + + @classmethod + def media_dir(cls, media_type, data_store=types.DataStore.HDD, verified=types.Verified.VERIFIED): + """Returns the directory path to a media directory""" + fp = join(cls.DataStorePath(data_store), cls.DIR_MEDIA, media_type.name.lower(), verified.name.lower()) + return fp + + # @classmethod + # def keyframe(cls, dir_media, idx, image_size=types.ImageSize.MEDIUM): + # """Returns path to keyframe image using supplied cls.media directory""" + # idx = str(idx).zfill(vcfg.ZERO_PADDING) + # size_label = vcfg.IMAGE_SIZE_LABELS[image_size] + # fp = join(dir_media, sha256_tree, sha256, idx, size_label, 'index.jpg') + # return fp + + @classmethod + def dnn(cls): + """Returns configurations for available DNNs""" + pass
\ No newline at end of file diff --git a/megapixels/app/settings/types.py b/megapixels/app/settings/types.py index e9107803..7157436d 100644 --- a/megapixels/app/settings/types.py +++ b/megapixels/app/settings/types.py @@ -7,7 +7,6 @@ def find_type(name, enum_type): return None - class FaceDetectNet(Enum): """Scene text detector networks""" HAAR, DLIB_CNN, DLIB_HOG, CVDNN, MTCNN = range(5) @@ -31,3 +30,14 @@ class HaarCascade(Enum): class LogLevel(Enum): """Loger vebosity""" DEBUG, INFO, WARN, ERROR, CRITICAL = range(5) + + +# --------------------------------------------------------------------- +# Metadata types +# -------------------------------------------------------------------- + +class Metadata(Enum): + IDENTITIES, POSES, ROIS, FILE_META, SHAS, UUIDS, FACE_VECTORS = range(7) + +class Dataset(Enum): + LFW, VGG_FACE2 = range(2) |