From 5270bd679c5ca28b71236d6b1f5b70856e8855fe Mon Sep 17 00:00:00 2001 From: Henry Ruhs Date: Wed, 22 Jan 2025 00:23:09 +0100 Subject: [PATCH] Follow yolo convention, renaming in face detector (#858) * Follow yolo convention, renaming in face detector * Follow yolo convention, renaming in face detector --- facefusion/choices.py | 2 +- facefusion/face_detector.py | 97 +++++++++++++++++++------------------ facefusion/program.py | 2 +- facefusion/typing.py | 2 +- 4 files changed, 53 insertions(+), 50 deletions(-) diff --git a/facefusion/choices.py b/facefusion/choices.py index df1f4f5..4f1cddd 100755 --- a/facefusion/choices.py +++ b/facefusion/choices.py @@ -9,7 +9,7 @@ face_detector_set : FaceDetectorSet =\ 'many': [ '640x640' ], 'retinaface': [ '160x160', '320x320', '480x480', '512x512', '640x640' ], 'scrfd': [ '160x160', '320x320', '480x480', '512x512', '640x640' ], - 'yoloface': [ '640x640' ] + 'yolo_face': [ '640x640' ] } face_detector_models : List[FaceDetectorModel] = list(face_detector_set.keys()) face_landmarker_models : List[FaceLandmarkerModel] = [ 'many', '2dfan4', 'peppa_wutz' ] diff --git a/facefusion/face_detector.py b/facefusion/face_detector.py index c698bed..5f57622 100644 --- a/facefusion/face_detector.py +++ b/facefusion/face_detector.py @@ -55,11 +55,11 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet: } } }, - 'yoloface': + 'yolo_face': { 'hashes': { - 'yoloface': + 'yolo_face': { 'url': resolve_download_url('models-3.0.0', 'yoloface_8n.hash'), 'path': resolve_relative_path('../.assets/models/yoloface_8n.hash') @@ -67,7 +67,7 @@ def create_static_model_set(download_scope : DownloadScope) -> ModelSet: }, 'sources': { - 'yoloface': + 'yolo_face': { 'url': resolve_download_url('models-3.0.0', 'yoloface_8n.onnx'), 'path': resolve_relative_path('../.assets/models/yoloface_8n.onnx') @@ -91,7 +91,7 @@ def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]: model_sources = {} model_set = create_static_model_set('full') - for face_detector_model in [ 'retinaface', 'scrfd', 'yoloface' ]: + for face_detector_model in [ 'retinaface', 'scrfd', 'yolo_face' ]: if state_manager.get_item('face_detector_model') in [ 'many', face_detector_model ]: model_hashes[face_detector_model] = model_set.get(face_detector_model).get('hashes').get(face_detector_model) model_sources[face_detector_model] = model_set.get(face_detector_model).get('sources').get(face_detector_model) @@ -122,8 +122,8 @@ def detect_faces(vision_frame : VisionFrame) -> Tuple[List[BoundingBox], List[Sc all_face_scores.extend(face_scores) all_face_landmarks_5.extend(face_landmarks_5) - if state_manager.get_item('face_detector_model') in [ 'many', 'yoloface' ]: - bounding_boxes, face_scores, face_landmarks_5 = detect_with_yoloface(vision_frame, state_manager.get_item('face_detector_size')) + if state_manager.get_item('face_detector_model') in [ 'many', 'yolo_face' ]: + bounding_boxes, face_scores, face_landmarks_5 = detect_with_yolo_face(vision_frame, state_manager.get_item('face_detector_size')) all_bounding_boxes.extend(bounding_boxes) all_face_scores.extend(face_scores) all_face_landmarks_5.extend(face_landmarks_5) @@ -149,6 +149,7 @@ def detect_with_retinaface(vision_frame : VisionFrame, face_detector_size : str) feature_strides = [ 8, 16, 32 ] feature_map_channel = 3 anchor_total = 2 + face_detector_score = state_manager.get_item('face_detector_score') face_detector_width, face_detector_height = unpack_resolution(face_detector_size) temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height)) ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0] @@ -157,29 +158,29 @@ def detect_with_retinaface(vision_frame : VisionFrame, face_detector_size : str) detection = forward_with_retinaface(detect_vision_frame) for index, feature_stride in enumerate(feature_strides): - keep_indices = numpy.where(detection[index] >= state_manager.get_item('face_detector_score'))[0] + keep_indices = numpy.where(detection[index] >= face_detector_score)[0] if numpy.any(keep_indices): stride_height = face_detector_height // feature_stride stride_width = face_detector_width // feature_stride anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width) - bounding_box_raw = detection[index + feature_map_channel] * feature_stride - face_landmark_5_raw = detection[index + feature_map_channel * 2] * feature_stride + bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride + face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride - for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]: + for bounding_box_raw in distance_to_bounding_box(anchors, bounding_boxes_raw)[keep_indices]: bounding_boxes.append(numpy.array( [ - bounding_box[0] * ratio_width, - bounding_box[1] * ratio_height, - bounding_box[2] * ratio_width, - bounding_box[3] * ratio_height, + bounding_box_raw[0] * ratio_width, + bounding_box_raw[1] * ratio_height, + bounding_box_raw[2] * ratio_width, + bounding_box_raw[3] * ratio_height ])) - for score in detection[index][keep_indices]: - face_scores.append(score[0]) + for face_score_raw in detection[index][keep_indices]: + face_scores.append(face_score_raw[0]) - for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]: - face_landmarks_5.append(face_landmark_5 * [ ratio_width, ratio_height ]) + for face_landmark_raw_5 in distance_to_face_landmark_5(anchors, face_landmarks_5_raw)[keep_indices]: + face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ]) return bounding_boxes, face_scores, face_landmarks_5 @@ -191,6 +192,7 @@ def detect_with_scrfd(vision_frame : VisionFrame, face_detector_size : str) -> T feature_strides = [ 8, 16, 32 ] feature_map_channel = 3 anchor_total = 2 + face_detector_score = state_manager.get_item('face_detector_score') face_detector_width, face_detector_height = unpack_resolution(face_detector_size) temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height)) ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0] @@ -199,65 +201,66 @@ def detect_with_scrfd(vision_frame : VisionFrame, face_detector_size : str) -> T detection = forward_with_scrfd(detect_vision_frame) for index, feature_stride in enumerate(feature_strides): - keep_indices = numpy.where(detection[index] >= state_manager.get_item('face_detector_score'))[0] + keep_indices = numpy.where(detection[index] >= face_detector_score)[0] if numpy.any(keep_indices): stride_height = face_detector_height // feature_stride stride_width = face_detector_width // feature_stride anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width) - bounding_box_raw = detection[index + feature_map_channel] * feature_stride - face_landmark_5_raw = detection[index + feature_map_channel * 2] * feature_stride + bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride + face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride - for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]: + for bounding_box_raw in distance_to_bounding_box(anchors, bounding_boxes_raw)[keep_indices]: bounding_boxes.append(numpy.array( [ - bounding_box[0] * ratio_width, - bounding_box[1] * ratio_height, - bounding_box[2] * ratio_width, - bounding_box[3] * ratio_height, + bounding_box_raw[0] * ratio_width, + bounding_box_raw[1] * ratio_height, + bounding_box_raw[2] * ratio_width, + bounding_box_raw[3] * ratio_height ])) - for score in detection[index][keep_indices]: - face_scores.append(score[0]) + for face_score_raw in detection[index][keep_indices]: + face_scores.append(face_score_raw[0]) - for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]: - face_landmarks_5.append(face_landmark_5 * [ ratio_width, ratio_height ]) + for face_landmark_raw_5 in distance_to_face_landmark_5(anchors, face_landmarks_5_raw)[keep_indices]: + face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ]) return bounding_boxes, face_scores, face_landmarks_5 -def detect_with_yoloface(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]: +def detect_with_yolo_face(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]: bounding_boxes = [] face_scores = [] face_landmarks_5 = [] + face_detector_score = state_manager.get_item('face_detector_score') face_detector_width, face_detector_height = unpack_resolution(face_detector_size) temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height)) ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0] ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1] detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size) - detection = forward_with_yoloface(detect_vision_frame) + detection = forward_with_yolo_face(detect_vision_frame) detection = numpy.squeeze(detection).T - bounding_box_raw, score_raw, face_landmark_5_raw = numpy.split(detection, [ 4, 5 ], axis = 1) - keep_indices = numpy.where(score_raw > state_manager.get_item('face_detector_score'))[0] + bounding_boxes_raw, face_scores_raw, face_landmarks_5_raw = numpy.split(detection, [ 4, 5 ], axis = 1) + keep_indices = numpy.where(face_scores_raw > face_detector_score)[0] if numpy.any(keep_indices): - bounding_box_raw, face_landmark_5_raw, score_raw = bounding_box_raw[keep_indices], face_landmark_5_raw[keep_indices], score_raw[keep_indices] + bounding_boxes_raw, face_scores_raw, face_landmarks_5_raw = bounding_boxes_raw[keep_indices], face_scores_raw[keep_indices], face_landmarks_5_raw[keep_indices] - for bounding_box in bounding_box_raw: + for bounding_box_raw in bounding_boxes_raw: bounding_boxes.append(numpy.array( [ - (bounding_box[0] - bounding_box[2] / 2) * ratio_width, - (bounding_box[1] - bounding_box[3] / 2) * ratio_height, - (bounding_box[0] + bounding_box[2] / 2) * ratio_width, - (bounding_box[1] + bounding_box[3] / 2) * ratio_height, + (bounding_box_raw[0] - bounding_box_raw[2] / 2) * ratio_width, + (bounding_box_raw[1] - bounding_box_raw[3] / 2) * ratio_height, + (bounding_box_raw[0] + bounding_box_raw[2] / 2) * ratio_width, + (bounding_box_raw[1] + bounding_box_raw[3] / 2) * ratio_height ])) - face_scores = score_raw.ravel().tolist() - face_landmark_5_raw[:, 0::3] = (face_landmark_5_raw[:, 0::3]) * ratio_width - face_landmark_5_raw[:, 1::3] = (face_landmark_5_raw[:, 1::3]) * ratio_height + face_scores = face_scores_raw.ravel().tolist() + face_landmarks_5_raw[:, 0::3] = (face_landmarks_5_raw[:, 0::3]) * ratio_width + face_landmarks_5_raw[:, 1::3] = (face_landmarks_5_raw[:, 1::3]) * ratio_height - for face_landmark_5 in face_landmark_5_raw: - face_landmarks_5.append(numpy.array(face_landmark_5.reshape(-1, 3)[:, :2])) + for face_landmark_raw_5 in face_landmarks_5_raw: + face_landmarks_5.append(numpy.array(face_landmark_raw_5.reshape(-1, 3)[:, :2])) return bounding_boxes, face_scores, face_landmarks_5 @@ -286,8 +289,8 @@ def forward_with_scrfd(detect_vision_frame : VisionFrame) -> Detection: return detection -def forward_with_yoloface(detect_vision_frame : VisionFrame) -> Detection: - face_detector = get_inference_pool().get('yoloface') +def forward_with_yolo_face(detect_vision_frame : VisionFrame) -> Detection: + face_detector = get_inference_pool().get('yolo_face') with thread_semaphore(): detection = face_detector.run(None, diff --git a/facefusion/program.py b/facefusion/program.py index d069664..ea0d832 100755 --- a/facefusion/program.py +++ b/facefusion/program.py @@ -94,7 +94,7 @@ def create_output_pattern_program() -> ArgumentParser: def create_face_detector_program() -> ArgumentParser: program = ArgumentParser(add_help = False) group_face_detector = program.add_argument_group('face detector') - group_face_detector.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_detector.face_detector_model', 'yoloface'), choices = facefusion.choices.face_detector_models) + group_face_detector.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_detector.face_detector_model', 'yolo_face'), choices = facefusion.choices.face_detector_models) known_args, _ = program.parse_known_args() face_detector_size_choices = facefusion.choices.face_detector_set.get(known_args.face_detector_model) group_face_detector.add_argument('--face-detector-size', help = wording.get('help.face_detector_size'), default = config.get_str_value('face_detector.face_detector_size', get_last(face_detector_size_choices)), choices = face_detector_size_choices) diff --git a/facefusion/typing.py b/facefusion/typing.py index 9bd7221..249ab9b 100755 --- a/facefusion/typing.py +++ b/facefusion/typing.py @@ -98,7 +98,7 @@ LogLevelSet = Dict[LogLevel, int] TableHeaders = List[str] TableContents = List[List[Any]] -FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yoloface'] +FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yolo_face'] FaceLandmarkerModel = Literal['many', '2dfan4', 'peppa_wutz'] FaceDetectorSet = Dict[FaceDetectorModel, List[str]] FaceSelectorMode = Literal['many', 'one', 'reference']