def run(image_path: str, weights_path: str):
config_logger(level='DEBUG', to_console=True)
person_detector = PersonDetector(weights_path=weights_path,
resize_height=192)
images_paths = list_images(image_path)
logger.info('Starting analysis...')
logger.info('Press "space" key to display next result. Press "q" to quit.')
max_image_size = 1920
drawer = Drawer()
drawer.font_scale = 0.5
drawer.font_linewidth = 1
for image_path in images_paths:
image_name = path.basename(image_path)
logger.info(f'Analyzing image {image_name}...')
image = cv.imread(image_path)
if image is None:
logger.warn(f'Unable to open image file {image_path}')
continue
h, w, = image.shape[0:2]
logger.info(f'Image loaded. Image size is {w}x{h} pixels.')
if max(w, h) > max_image_size:
image, scale = resize(image, max_image_size)
h, w, = image.shape[0:2]
logger.info(f'Image resized to {w}x{h} pixels.')
tic = time()
boxes, scores = person_detector.detect(image)
toc = time()
logger.info(f'Found {len(boxes)} persons in {(toc - tic):.3f} s.')
for ind, box in enumerate(boxes):
drawer.draw_labeled_box(image, f'{int(100*scores[ind])}%', box)
cv.imshow(f'Faces in {image_name}', image)
ret = cv.waitKey()
if ret == ord(' '):
cv.destroyAllWindows()
elif ret == ord('q'):
cv.destroyAllWindows()
break
def run(
image_path: str,
detector_weights_path: str,
marker_weights_path: str,
encoder_weights_path: str,
show_scores: bool = False
):
from dnfal.vision import FacesVision
from dnfal.settings import Settings
from dnfal.loggers import logger
settings = Settings()
settings.detector_weights_path = detector_weights_path
settings.marker_weights_path = marker_weights_path
settings.encoder_weights_path = encoder_weights_path
settings.log_to_console = True
settings.detection_min_height = 24
settings.detection_min_score = 0.8
settings.marking_min_score = 0.6
faces_vision = FacesVision(settings)
if path.isdir(image_path):
image_paths = list_files(image_path, IMAGE_EXT, recursive=True)
if len(image_paths) == 0:
raise ValueError(f'No images found in {image_path}.')
elif path.isfile(image_path):
image_paths = [image_path]
else:
raise ValueError(f'Input "{image_path}" is not file nor a directory.')
logger.info('Starting analysis...')
logger.info('Press "space" key to display next result. Press "q" to quit.')
max_image_size = 1920
drawer = Drawer()
drawer.font_scale = 0.7
drawer.font_linewidth = 2
drawer.font_color = (0, 255, 0)
for image_path in image_paths:
image_name = path.basename(image_path)
image = cv.imread(image_path)
if image is None:
logger.warn(f'Unable to open image file {image_path}')
continue
h, w, = image.shape[0:2]
logger.info(f'{image_name} loaded. Image size is {w}x{h} pixels.')
if max(w, h) > max_image_size:
image, scale = resize(image, max_image_size)
h, w, = image.shape[0:2]
logger.info(f'Image resized to {w}x{h} pixels.')
tic = time()
faces, _ = faces_vision.frame_analyzer.find_faces(image)
toc = time()
logger.info(f'Found {len(faces)} faces in {(toc - tic):.3f} seconds.')
for ind, face in enumerate(faces):
face_image = face.image.copy()
box = (
int(w * face.box[0]),
int(h * face.box[1]),
int(w * face.box[2]),
int(h * face.box[3]),
)
if show_scores:
s = (int(100 * face.detect_score), int(100 * face.mark_score))
label = f'Face {ind}, ({s[0]} %, {s[1]} %)'
else:
label = f'Face {ind}'
drawer.draw_labeled_box(image, label, box)
for m in face.landmarks:
cv.circle(face_image, (m[0], m[1]), 2, (0, 255, 0), -1)
nv = face.nose_deviation
print(
f'Detected face [{ind}]: {{ score: {face.detect_score}, '
f'nose deviation: [{nv[0]:.3f}, {nv[1]:.3f}] }}'
)
cv.imshow(f'Face "{ind}"', face_image)
cv.imshow(f'Faces in {image_name}', image)
ret = cv.waitKey()
if ret == ord(' '):
cv.destroyAllWindows()
elif ret == ord('q'):
cv.destroyAllWindows()
break
def run(image_path: str, detector_weights_path: str, marker_weights_path: str):
from dnfal.amazon.faces import analyze_faces, AwsFace
from dnfal.detection import FaceDetector
from dnfal.alignment import FaceMarker, FaceAligner
from dnfal.engine import FrameAnalyzer
from dnfal.loggers import logger, config_logger
config_logger(level='info')
face_detector = FaceDetector(weights_path=detector_weights_path,
min_score=0.9,
nms_thresh=0.7)
face_marker = FaceMarker(weights_path=marker_weights_path)
face_aligner = FaceAligner(out_size=256)
frame_analyzer = FrameAnalyzer(detector=face_detector,
marker=face_marker,
aligner=face_aligner,
encoder=None,
face_padding=0.4,
store_aligned=True)
if path.isdir(image_path):
image_paths = list_files(image_path, IMAGE_EXT, recursive=True)
if len(image_paths) == 0:
raise ValueError(f'No images found in {image_path}.')
elif path.isfile(image_path):
image_paths = [image_path]
else:
raise ValueError(f'Input "{image_path}" is not file nor a directory.')
logger.info('Starting analysis...')
logger.info('Press "space" key to display next result. Press "q" to quit.')
max_image_size = 1920
drawer = Drawer()
drawer.font_scale = 0.5
drawer.font_linewidth = 1
drawer.text_margins = (2, 3, 12, 3)
GENDER_LABELS = {
AwsFace.GENDER_MAN: 'Man',
AwsFace.GENDER_WOMAN: 'Woman',
}
for image_path in image_paths:
image_name = path.basename(image_path)
image = cv.imread(image_path)
if image is None:
logger.warn(f'Unable to open image file {image_path}')
continue
h, w, = image.shape[0:2]
logger.info(f'{image_name} loaded. Image size is {w}x{h} pixels.')
if max(w, h) > max_image_size:
image, scale = resize(image, max_image_size)
h, w, = image.shape[0:2]
logger.info(f'Image resized to {w}x{h} pixels.')
image = cv.copyMakeBorder(image,
left=0,
top=100,
right=0,
bottom=0,
borderType=cv.BORDER_CONSTANT,
value=(0, 0, 0))
h, w, = image.shape[0:2]
tic = time()
faces, _ = frame_analyzer.find_faces(image)
n_faces = len(faces)
toc = time()
logger.info(f'Found {n_faces} faces in {(toc - tic):.3f} seconds.')
if n_faces:
tic = time()
aws_faces = analyze_faces([face.image for face in faces])
delay = time() - tic
logger.info(f'Faces analyzed in {delay:.3f} seconds.')
for ind, face in enumerate(faces):
gender_label = 'Unknown gender'
age_label = 'Unknown age'
aws_face = aws_faces[ind]
if aws_face is not None:
gender_pred = GENDER_LABELS[aws_face.gender]
gender_prob = 100 * aws_face.gender_score
age_low = aws_face.age_low
age_high = aws_face.age_high
gender_label = f'{gender_pred} ({int(gender_prob)}%)'
age_label = f'{age_low}-{age_high} years'
label = f'{gender_label} \n {age_label}'
box = (
int(w * face.box[0]),
int(h * face.box[1]),
int(w * face.box[2]),
int(h * face.box[3]),
)
drawer.draw_labeled_box(image, label, box)
cv.imshow(f'Faces in {image_name}', image)
ret = cv.waitKey()
if ret == ord(' '):
cv.destroyAllWindows()
elif ret == ord('q'):
cv.destroyAllWindows()
break
def run(image_path: str, output_path: str, weights_path: str):
config_logger(level='DEBUG', to_console=True)
person_encoder = PersonEncoder(weights_path=weights_path)
images_paths = list_images(image_path)
logger.info('Starting analysis...')
logger.info('Press "space" key to display next result. Press "q" to quit.')
drawer = Drawer()
drawer.font_scale = 0.5
drawer.font_linewidth = 1
images = []
for image_path in images_paths:
image_name = path.basename(image_path)
logger.info(f'Reading image {image_name}...')
image = cv.imread(image_path)
if image is None:
logger.warn(f'Unable to open image file {image_path}')
continue
h, w, = image.shape[0:2]
logger.info(f'Image loaded. Image size is {w}x{h} pixels.')
images.append(image)
logger.info(f'Starting encoding images...')
tic = time()
embeddings = person_encoder.encode(images)
toc = time()
logger.info(f'Encoding {len(images)} images took {(toc - tic):.3f} s.')
score_matrix = np.matmul(embeddings, embeddings.T)
logger.info(f'Building matching results image...')
n_images = len(images)
grid_width = (n_images + 1) * (SHOW_WIDTH +
SHOW_MARGIN[0]) + SHOW_MARGIN[0]
grid_height = (n_images + 1) * (SHOW_HEIGHT +
SHOW_MARGIN[1]) + SHOW_MARGIN[1]
show_grid = np.zeros((grid_height, grid_width, 3), dtype=np.uint8)
y = SHOW_MARGIN[1]
for i in range(n_images):
x = SHOW_MARGIN[0]
image_row = resize_grid_item(images[i])
h, w = image_row.shape[0:2]
show_grid[y:(y + h), x:(x + w)] = image_row
cv.rectangle(img=show_grid,
pt1=(x, y),
pt2=(x + w, y + h),
color=(0, 0, 255),
thickness=1,
lineType=cv.LINE_AA)
x += SHOW_WIDTH + SHOW_MARGIN[0]
sort_score_ind = np.argsort(score_matrix[i, :])[::-1]
row_score = score_matrix[i, sort_score_ind]
row_images = [images[i] for i in sort_score_ind]
for j in range(n_images):
image_col = resize_grid_item(row_images[j])
h, w = image_col.shape[0:2]
show_grid[y:(y + h), x:(x + w)] = image_col
score = row_score[j]
cv.putText(img=show_grid,
text=f'{int(100 * score)}%',
org=(x, y + SHOW_HEIGHT + 13),
color=(255, 255, 255),
fontFace=cv.FONT_HERSHEY_PLAIN,
fontScale=0.8,
lineType=cv.LINE_AA)
x += SHOW_WIDTH + SHOW_MARGIN[0]
y += SHOW_HEIGHT + SHOW_MARGIN[1]
logger.info(f'Saving matching results image...')
cv.imwrite(output_path, show_grid)
logger.info(f'Showing matching results image...')
window_name = 'Person matching scoring matrix'
cv.namedWindow(window_name, cv.WINDOW_NORMAL)
cv.resizeWindow(window_name, 1800, 1000)
cv.imshow(window_name, show_grid)
if cv.waitKey() == ord('q'):
cv.destroyAllWindows()
logger.info(f'Done !!')
def run(video_path: str,
output_path: str,
detector_weights_path: str,
marker_weights_path: str,
encoder_weights_path: str,
show: bool = True,
real_time: bool = False):
drawer = Drawer()
drawer.font_scale = 1
settings = Settings()
settings.detector_weights_path = detector_weights_path
settings.marker_weights_path = marker_weights_path
settings.encoder_weights_path = encoder_weights_path
settings.video_detect_interval = 0.5
settings.align_max_deviation = (0.4, 0.3)
settings.detection_min_score = 0.95
settings.detection_only = False
settings.detection_min_height = 24
settings.detection_face_padding = 0.2
settings.video_capture_source = video_path
settings.logging_level = 'debug'
settings.log_to_console = True
settings.video_mode = VideoAnalyzer.MODE_ALL
settings.video_real_time = real_time
settings.store_face_frames = True
faces_vision = FacesVision(settings)
def on_subject_updated(face: Face):
subject = face.subject
filename = f'{subject.key}_{len(subject.faces)}.jpg'
cv.imwrite(path.join(output_path, filename), face.image)
def on_frame():
frame = faces_vision.video_analyzer.frame
h, w, = frame.shape[0:2]
avg_roi = faces_vision.video_analyzer.adaptive_roi._avg_roi
roi_dev = faces_vision.video_analyzer.adaptive_roi._roi_dev
roi = faces_vision.video_analyzer.adaptive_roi.roi
if roi is not None:
box = (
int(w * roi[0]),
int(h * roi[1]),
int(w * roi[2]),
int(h * roi[3]),
)
drawer.box_color = (0, 0, 255)
drawer.draw_labeled_box(frame, f'Roi, dev = {roi_dev:.3f}', box)
elif avg_roi is not None:
box = (
int(w * avg_roi[0]),
int(h * avg_roi[1]),
int(w * avg_roi[2]),
int(h * avg_roi[3]),
)
drawer.box_color = (255, 0, 0)
drawer.draw_labeled_box(frame, f'Avg Roi, dev = {roi_dev:.3f}',
box)
cv.imshow(f'Video {video_path}', frame)
ret = cv.waitKey(1)
if ret == ord('q'):
cv.destroyAllWindows()
faces_vision.video_analyzer.stop()
faces_vision.video_analyzer.run(update_subject_callback=on_subject_updated,
frame_callback=on_frame if show else None)