Spaces:
Runtime error
Runtime error
File size: 2,654 Bytes
3650c12 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
# Copyright (c) 2024 Bytedance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import mediapipe as mp
from latentsync.utils.util import read_video, gather_video_paths_recursively
import os
import tqdm
from multiprocessing import Pool
class FaceDetector:
def __init__(self):
self.face_detection = mp.solutions.face_detection.FaceDetection(
model_selection=0, min_detection_confidence=0.5
)
def detect_face(self, image):
# Process the image and detect faces.
results = self.face_detection.process(image)
if not results.detections: # Face not detected
return False
if len(results.detections) != 1:
return False
return True
def detect_video(self, video_path):
try:
video_frames = read_video(video_path, change_fps=False)
except Exception as e:
print(f"Exception: {e} - {video_path}")
return False
if len(video_frames) == 0:
return False
for frame in video_frames:
if not self.detect_face(frame):
return False
return True
def close(self):
self.face_detection.close()
def remove_incorrect_affined(video_path):
if not os.path.isfile(video_path):
return
face_detector = FaceDetector()
has_face = face_detector.detect_video(video_path)
if not has_face:
os.remove(video_path)
print(f"Removed: {video_path}")
face_detector.close()
def remove_incorrect_affined_multiprocessing(input_dir, num_workers):
video_paths = gather_video_paths_recursively(input_dir)
print(f"Total videos: {len(video_paths)}")
print(f"Removing incorrect affined videos in {input_dir} ...")
with Pool(num_workers) as pool:
for _ in tqdm.tqdm(pool.imap_unordered(remove_incorrect_affined, video_paths), total=len(video_paths)):
pass
if __name__ == "__main__":
input_dir = "/mnt/bn/maliva-gen-ai-v2/chunyu.li/multilingual_dcc/high_visual_quality"
num_workers = 50
remove_incorrect_affined_multiprocessing(input_dir, num_workers)
|