mirror of
https://github.com/serengil/deepface.git
synced 2025-06-06 11:35:21 +00:00
change behaviour in special case batched single image
This commit is contained in:
galthran-wq
parent
93b8af100b
commit
8b1b465d22
@ -49,10 +49,11 @@ class CenterFaceClient(Detector):
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]):
|
||||
A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if not isinstance(img, list):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
results = [self._process_single_image(single_img) for single_img in img]
|
||||
if len(results) == 1:
|
||||
if not is_batched_input:
|
||||
return results[0]
|
||||
return results
|
||||
|
||||
|
||||
@ -62,10 +62,11 @@ class DlibClient(Detector):
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]):
|
||||
A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if not isinstance(img, list):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
results = [self._process_single_image(single_img) for single_img in img]
|
||||
if len(results) == 1:
|
||||
if not is_batched_input:
|
||||
return results[0]
|
||||
return results
|
||||
|
||||
|
||||
@ -32,10 +32,11 @@ class FastMtCnnClient(Detector):
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]):
|
||||
A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if not isinstance(img, list):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
results = [self._process_single_image(single_img) for single_img in img]
|
||||
if len(results) == 1:
|
||||
if not is_batched_input:
|
||||
return results[0]
|
||||
return results
|
||||
|
||||
|
||||
@ -58,10 +58,11 @@ class MediaPipeClient(Detector):
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]):
|
||||
A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if not isinstance(img, list):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
results = [self._process_single_image(single_img) for single_img in img]
|
||||
if len(results) == 1:
|
||||
if not is_batched_input:
|
||||
return results[0]
|
||||
return results
|
||||
|
||||
|
||||
@ -38,7 +38,8 @@ class MtCnnClient(Detector):
|
||||
or a list of lists of FacialAreaRegion objects for each image
|
||||
"""
|
||||
|
||||
if not isinstance(img, list):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
|
||||
resp = []
|
||||
@ -76,7 +77,7 @@ class MtCnnClient(Detector):
|
||||
|
||||
resp.append(image_resp)
|
||||
|
||||
if len(resp) == 1:
|
||||
if not is_batched_input:
|
||||
return resp[0]
|
||||
return resp
|
||||
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
# built-in dependencies
|
||||
import os
|
||||
from typing import Any, List, Union
|
||||
import logging
|
||||
|
||||
# 3rd party dependencies
|
||||
import cv2
|
||||
@ -9,6 +10,7 @@ import numpy as np
|
||||
#project dependencies
|
||||
from deepface.models.Detector import Detector, FacialAreaRegion
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class OpenCvClient(Detector):
|
||||
"""
|
||||
@ -17,6 +19,7 @@ class OpenCvClient(Detector):
|
||||
|
||||
def __init__(self):
|
||||
self.model = self.build_model()
|
||||
self.supports_batch_detection = self._supports_batch_detection()
|
||||
|
||||
def build_model(self):
|
||||
"""
|
||||
@ -28,6 +31,19 @@ class OpenCvClient(Detector):
|
||||
detector["face_detector"] = self.__build_cascade("haarcascade")
|
||||
detector["eye_detector"] = self.__build_cascade("haarcascade_eye")
|
||||
return detector
|
||||
|
||||
def _supports_batch_detection(self) -> bool:
|
||||
supports_batch_detection = os.getenv(
|
||||
"ENABLE_OPENCV_BATCH_DETECTION", "false"
|
||||
).lower() == "true"
|
||||
if not supports_batch_detection:
|
||||
logger.warning(
|
||||
"Batch detection is disabled for opencv by default "
|
||||
"since the results are not consistent with single image detection. "
|
||||
"You can force enable it by setting the environment variable "
|
||||
"ENABLE_OPENCV_BATCH_DETECTION to true."
|
||||
)
|
||||
return supports_batch_detection
|
||||
|
||||
def detect_faces(
|
||||
self,
|
||||
@ -46,8 +62,10 @@ class OpenCvClient(Detector):
|
||||
"""
|
||||
if isinstance(img, np.ndarray):
|
||||
imgs = [img]
|
||||
else:
|
||||
elif self.supports_batch_detection:
|
||||
imgs = img
|
||||
else:
|
||||
return [self.detect_faces(single_img) for single_img in img]
|
||||
|
||||
batch_results = []
|
||||
|
||||
|
||||
@ -28,7 +28,8 @@ class RetinaFaceClient(Detector):
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]):
|
||||
A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if isinstance(img, np.ndarray):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
imgs = [img]
|
||||
else:
|
||||
imgs = img
|
||||
@ -81,4 +82,6 @@ class RetinaFaceClient(Detector):
|
||||
|
||||
batch_results.append(resp)
|
||||
|
||||
return batch_results if len(batch_results) > 1 else batch_results[0]
|
||||
if not is_batched_input:
|
||||
return batch_results[0]
|
||||
return batch_results
|
||||
|
||||
@ -69,81 +69,89 @@ class SsdClient(Detector):
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]):
|
||||
A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if isinstance(img, np.ndarray):
|
||||
imgs = [img]
|
||||
else:
|
||||
imgs = img
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
results = [self._process_single_image(single_img) for single_img in img]
|
||||
if not is_batched_input:
|
||||
return results[0]
|
||||
return results
|
||||
|
||||
batch_results = []
|
||||
def _process_single_image(self, single_img: np.ndarray) -> List[FacialAreaRegion]:
|
||||
"""
|
||||
Helper function to detect faces in a single image.
|
||||
|
||||
for single_img in imgs:
|
||||
# Because cv2.dnn.blobFromImage expects CV_8U (8-bit unsigned integer) values
|
||||
if single_img.dtype != np.uint8:
|
||||
single_img = single_img.astype(np.uint8)
|
||||
Args:
|
||||
single_img (np.ndarray): Pre-loaded image as numpy array
|
||||
|
||||
opencv_module: OpenCv.OpenCvClient = self.model["opencv_module"]
|
||||
Returns:
|
||||
results (List[FacialAreaRegion]): A list of FacialAreaRegion objects
|
||||
"""
|
||||
# Because cv2.dnn.blobFromImage expects CV_8U (8-bit unsigned integer) values
|
||||
if single_img.dtype != np.uint8:
|
||||
single_img = single_img.astype(np.uint8)
|
||||
|
||||
target_size = (300, 300)
|
||||
original_size = single_img.shape
|
||||
current_img = cv2.resize(single_img, target_size)
|
||||
opencv_module: OpenCv.OpenCvClient = self.model["opencv_module"]
|
||||
|
||||
aspect_ratio_x = original_size[1] / target_size[1]
|
||||
aspect_ratio_y = original_size[0] / target_size[0]
|
||||
target_size = (300, 300)
|
||||
original_size = single_img.shape
|
||||
current_img = cv2.resize(single_img, target_size)
|
||||
|
||||
imageBlob = cv2.dnn.blobFromImage(image=current_img)
|
||||
aspect_ratio_x = original_size[1] / target_size[1]
|
||||
aspect_ratio_y = original_size[0] / target_size[0]
|
||||
|
||||
face_detector = self.model["face_detector"]
|
||||
face_detector.setInput(imageBlob)
|
||||
detections = face_detector.forward()
|
||||
imageBlob = cv2.dnn.blobFromImage(image=current_img)
|
||||
|
||||
class ssd_labels(IntEnum):
|
||||
img_id = 0
|
||||
is_face = 1
|
||||
confidence = 2
|
||||
left = 3
|
||||
top = 4
|
||||
right = 5
|
||||
bottom = 6
|
||||
face_detector = self.model["face_detector"]
|
||||
face_detector.setInput(imageBlob)
|
||||
detections = face_detector.forward()
|
||||
|
||||
faces = detections[0][0]
|
||||
faces = faces[
|
||||
(faces[:, ssd_labels.is_face] == 1) & (faces[:, ssd_labels.confidence] >= 0.90)
|
||||
]
|
||||
margins = [ssd_labels.left, ssd_labels.top, ssd_labels.right, ssd_labels.bottom]
|
||||
faces[:, margins] = np.int32(faces[:, margins] * 300)
|
||||
faces[:, margins] = np.int32(
|
||||
faces[:, margins] * [aspect_ratio_x, aspect_ratio_y, aspect_ratio_x, aspect_ratio_y]
|
||||
class ssd_labels(IntEnum):
|
||||
img_id = 0
|
||||
is_face = 1
|
||||
confidence = 2
|
||||
left = 3
|
||||
top = 4
|
||||
right = 5
|
||||
bottom = 6
|
||||
|
||||
faces = detections[0][0]
|
||||
faces = faces[
|
||||
(faces[:, ssd_labels.is_face] == 1) & (faces[:, ssd_labels.confidence] >= 0.90)
|
||||
]
|
||||
margins = [ssd_labels.left, ssd_labels.top, ssd_labels.right, ssd_labels.bottom]
|
||||
faces[:, margins] = np.int32(faces[:, margins] * 300)
|
||||
faces[:, margins] = np.int32(
|
||||
faces[:, margins] * [aspect_ratio_x, aspect_ratio_y, aspect_ratio_x, aspect_ratio_y]
|
||||
)
|
||||
faces[:, [ssd_labels.right, ssd_labels.bottom]] -= faces[
|
||||
:, [ssd_labels.left, ssd_labels.top]
|
||||
]
|
||||
|
||||
resp = []
|
||||
for face in faces:
|
||||
confidence = float(face[ssd_labels.confidence])
|
||||
x, y, w, h = map(int, face[margins])
|
||||
detected_face = single_img[y : y + h, x : x + w]
|
||||
|
||||
left_eye, right_eye = opencv_module.find_eyes(detected_face)
|
||||
|
||||
# eyes found in the detected face instead image itself
|
||||
# detected face's coordinates should be added
|
||||
if left_eye is not None:
|
||||
left_eye = x + int(left_eye[0]), y + int(left_eye[1])
|
||||
if right_eye is not None:
|
||||
right_eye = x + int(right_eye[0]), y + int(right_eye[1])
|
||||
|
||||
facial_area = FacialAreaRegion(
|
||||
x=x,
|
||||
y=y,
|
||||
w=w,
|
||||
h=h,
|
||||
left_eye=left_eye,
|
||||
right_eye=right_eye,
|
||||
confidence=confidence,
|
||||
)
|
||||
faces[:, [ssd_labels.right, ssd_labels.bottom]] -= faces[
|
||||
:, [ssd_labels.left, ssd_labels.top]
|
||||
]
|
||||
resp.append(facial_area)
|
||||
|
||||
resp = []
|
||||
for face in faces:
|
||||
confidence = float(face[ssd_labels.confidence])
|
||||
x, y, w, h = map(int, face[margins])
|
||||
detected_face = single_img[y : y + h, x : x + w]
|
||||
|
||||
left_eye, right_eye = opencv_module.find_eyes(detected_face)
|
||||
|
||||
# eyes found in the detected face instead image itself
|
||||
# detected face's coordinates should be added
|
||||
if left_eye is not None:
|
||||
left_eye = x + int(left_eye[0]), y + int(left_eye[1])
|
||||
if right_eye is not None:
|
||||
right_eye = x + int(right_eye[0]), y + int(right_eye[1])
|
||||
|
||||
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)
|
||||
|
||||
batch_results.append(resp)
|
||||
|
||||
return batch_results if len(batch_results) > 1 else batch_results[0]
|
||||
return resp
|
||||
|
||||
@ -67,10 +67,11 @@ class YuNetClient(Detector):
|
||||
Returns:
|
||||
results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]): A list or a list of lists of FacialAreaRegion objects
|
||||
"""
|
||||
if not isinstance(img, list):
|
||||
is_batched_input = isinstance(img, list)
|
||||
if not is_batched_input:
|
||||
img = [img]
|
||||
results = [self._process_single_image(single_img) for single_img in img]
|
||||
if len(results) == 1:
|
||||
if not is_batched_input:
|
||||
return results[0]
|
||||
return results
|
||||
|
||||
|
||||
@ -82,15 +82,23 @@ def extract_faces(
|
||||
just available in the result only if anti_spoofing is set to True in input arguments.
|
||||
"""
|
||||
|
||||
if isinstance(img_path, np.ndarray) and img_path.ndim == 4:
|
||||
img_path = [img_path[i] for i in range(img_path.shape[0])]
|
||||
if not isinstance(img_path, list):
|
||||
img_path = [img_path]
|
||||
batched_input = (
|
||||
(
|
||||
isinstance(img_path, np.ndarray) and
|
||||
img_path.ndim == 4
|
||||
) or isinstance(img_path, list)
|
||||
)
|
||||
if not batched_input:
|
||||
imgs_path = [img_path]
|
||||
elif isinstance(img_path, np.ndarray):
|
||||
imgs_path = [img_path[i] for i in range(img_path.shape[0])]
|
||||
else:
|
||||
imgs_path = img_path
|
||||
|
||||
all_images = []
|
||||
img_names = []
|
||||
|
||||
for single_img_path in img_path:
|
||||
for single_img_path in imgs_path:
|
||||
# img might be path, base64 or numpy array. Convert it to numpy whatever it is.
|
||||
img, img_name = image_utils.load_image(single_img_path)
|
||||
|
||||
@ -109,9 +117,6 @@ def extract_faces(
|
||||
max_faces=max_faces,
|
||||
)
|
||||
|
||||
if len(all_images) == 1:
|
||||
all_face_objs = [all_face_objs]
|
||||
|
||||
all_resp_objs = []
|
||||
|
||||
for img, img_name, face_objs in zip(all_images, img_names, all_face_objs):
|
||||
@ -203,7 +208,7 @@ def extract_faces(
|
||||
|
||||
all_resp_objs.append(img_resp_objs)
|
||||
|
||||
if len(all_resp_objs) == 1:
|
||||
if not batched_input:
|
||||
return all_resp_objs[0]
|
||||
return all_resp_objs
|
||||
|
||||
@ -239,8 +244,18 @@ def detect_faces(
|
||||
|
||||
- confidence (float): The confidence score associated with the detected face.
|
||||
"""
|
||||
if not isinstance(img, list):
|
||||
img = [img]
|
||||
batched_input = (
|
||||
(
|
||||
isinstance(img, np.ndarray) and
|
||||
img.ndim == 4
|
||||
) or isinstance(img, list)
|
||||
)
|
||||
if not batched_input:
|
||||
imgs = [img]
|
||||
elif isinstance(img, np.ndarray):
|
||||
imgs = [img[i] for i in range(img.shape[0])]
|
||||
else:
|
||||
imgs = img
|
||||
|
||||
if detector_backend == "skip":
|
||||
all_face_objs = [
|
||||
@ -253,9 +268,9 @@ def detect_faces(
|
||||
confidence=0,
|
||||
)
|
||||
]
|
||||
for single_img in img
|
||||
for single_img in imgs
|
||||
]
|
||||
if len(img) == 1:
|
||||
if not batched_input:
|
||||
all_face_objs = all_face_objs[0]
|
||||
return all_face_objs
|
||||
|
||||
@ -266,7 +281,7 @@ def detect_faces(
|
||||
preprocessed_images = []
|
||||
width_borders = []
|
||||
height_borders = []
|
||||
for single_img in img:
|
||||
for single_img in imgs:
|
||||
height, width, _ = single_img.shape
|
||||
|
||||
# validate expand percentage score
|
||||
@ -299,9 +314,6 @@ def detect_faces(
|
||||
# Detect faces in all preprocessed images
|
||||
all_facial_areas = face_detector.detect_faces(preprocessed_images)
|
||||
|
||||
if len(preprocessed_images) == 1:
|
||||
all_facial_areas = [all_facial_areas]
|
||||
|
||||
all_detected_faces = []
|
||||
for (
|
||||
single_img,
|
||||
@ -336,7 +348,7 @@ def detect_faces(
|
||||
|
||||
all_detected_faces.append(detected_faces)
|
||||
|
||||
if len(all_detected_faces) == 1:
|
||||
if not batched_input:
|
||||
return all_detected_faces[0]
|
||||
return all_detected_faces
|
||||
|
||||
|
||||
@ -242,8 +242,8 @@ def test_batch_extract_faces_single_image():
|
||||
img_path=[img_path],
|
||||
align=True,
|
||||
)
|
||||
assert len(imgs_objs_batch) == 2
|
||||
assert [isinstance(obj, dict) for obj in imgs_objs_batch]
|
||||
assert len(imgs_objs_batch) == 1 and isinstance(imgs_objs_batch[0], list)
|
||||
assert [isinstance(obj, dict) for obj in imgs_objs_batch[0]]
|
||||
|
||||
|
||||
def test_backends_for_enforced_detection_with_non_facial_inputs():
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user