taotaonice / FaceShifter

Try to reproduce FaceShifter
250 stars 62 forks source link

Bad MTCNN detection performance #44

Open ocastan opened 3 years ago

ocastan commented 3 years ago

IMHO this is due to MTCNN weights trained with RGB images whereas OpenCV use BGR: changing channels order from BGR to RGB before calling detector.align in inference_demo.py or online_preview.py or before calling mtcnn.align_multi in preprocess_images.py (and always restoring BGR after since AEI is trained with BGR images), give me far better face detection