github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-07 12:05:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

yolo detect batched

Browse Source
This commit is contained in:
galthran-wq 2025-02-12 15:59:13 +00:00
parent b2d6178bed
commit 1bd83356e7
1 changed files with 54 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

95
deepface/models/face_detection/Yolo.py
View File

@ -1,6 +1,6 @@
# built-in dependencies # built-in dependencies
import os import os
from typing import List, Any from typing import List, Any, Union, Tuple
from enum import Enum from enum import Enum
# 3rd party dependencies # 3rd party dependencies
@ -62,64 +62,77 @@ class YoloDetectorClient(Detector):
# Return face_detector # Return face_detector
return YOLO(weight_file) return YOLO(weight_file)
def detect_faces(self, img: np.ndarray) -> List[FacialAreaRegion]: def detect_faces(self, imgs: Union[np.ndarray, List[np.ndarray]]) -> Union[List[List[FacialAreaRegion]], List[FacialAreaRegion]]:
""" """
Detect and align face with yolo Detect and align faces in an image or a list of images with yolo
Args: Args:
img (np.ndarray): pre-loaded image as numpy array imgs (Union[np.ndarray, List[np.ndarray]]): pre-loaded image as numpy array or a list of those
Returns: Returns:
results (List[FacialAreaRegion]): A list of FacialAreaRegion objects results (Union[List[List[FacialAreaRegion]], List[FacialAreaRegion]]):
A list of lists of FacialAreaRegion objects for each image or a list of FacialAreaRegion objects
""" """
resp = [] if not isinstance(imgs, list):
imgs = [imgs]
# Detect faces all_results = []
results = self.model.predict(
img, # Detect faces for all images
results_list = self.model.predict(
imgs,
verbose=False, verbose=False,
show=False, show=False,
conf=float(os.getenv("YOLO_MIN_DETECTION_CONFIDENCE", "0.25")), conf=float(os.getenv("YOLO_MIN_DETECTION_CONFIDENCE", "0.25")),
)[0] )
# For each face, extract the bounding box, the landmarks and confidence # Iterate over each image's results
for result in results: for results in results_list:
resp = []
if result.boxes is None: # For each face, extract the bounding box, the landmarks and confidence
continue for result in results:
# Extract the bounding box and the confidence if result.boxes is None:
x, y, w, h = result.boxes.xywh.tolist()[0] continue
confidence = result.boxes.conf.tolist()[0]
right_eye = None # Extract the bounding box and the confidence
left_eye = None x, y, w, h = result.boxes.xywh.tolist()[0]
confidence = result.boxes.conf.tolist()[0]
# yolo-facev8 is detecting eyes through keypoints, right_eye = None
# while for v11 keypoints are always None left_eye = None
if result.keypoints is not None:
# right_eye_conf = result.keypoints.conf[0][0]
# left_eye_conf = result.keypoints.conf[0][1]
right_eye = result.keypoints.xy[0][0].tolist()
left_eye = result.keypoints.xy[0][1].tolist()
# eyes are list of float, need to cast them tuple of int # yolo-facev8 is detecting eyes through keypoints,
left_eye = tuple(int(i) for i in left_eye) # while for v11 keypoints are always None
right_eye = tuple(int(i) for i in right_eye) if result.keypoints is not None:
# right_eye_conf = result.keypoints.conf[0][0]
# left_eye_conf = result.keypoints.conf[0][1]
right_eye = result.keypoints.xy[0][0].tolist()
left_eye = result.keypoints.xy[0][1].tolist()
x, y, w, h = int(x - w / 2), int(y - h / 2), int(w), int(h) # eyes are list of float, need to cast them tuple of int
facial_area = FacialAreaRegion( # Ensure eyes are tuples of exactly two integers or None
x=x, left_eye = tuple(map(int, left_eye[:2])) if left_eye and len(left_eye) == 2 else None
y=y, right_eye = tuple(map(int, right_eye[:2])) if right_eye and len(right_eye) == 2 else None
w=w,
h=h,
left_eye=left_eye,
right_eye=right_eye,
confidence=confidence,
)
resp.append(facial_area)
return resp x, y, w, h = int(x - w / 2), int(y - h / 2), int(w), int(h)
facial_area = FacialAreaRegion(
x=x,
y=y,
w=w,
h=h,
left_eye=left_eye,
right_eye=right_eye,
confidence=confidence,
)
resp.append(facial_area)
all_results.append(resp)
if len(all_results) == 1:
return all_results[0]
return all_results
class YoloDetectorClientV8n(YoloDetectorClient): class YoloDetectorClientV8n(YoloDetectorClient):