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
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