Revision history [back]

your labels should be CvType.CV_32SC1, not CvType.CV_8UC1

• your labels should be CvType.CV_32SC1, not CvType.CV_8UC1
• the yale db is grayscale, it's somewhat "unfair", trying with facenet here, which expects color images
• a 50/50 split is not good, given that the db is somewhat an ordered sequence of lighting conditions. please lookup, how "cross-validation" works, and rather use 5 or 10 fold CV.
• your BIF params will make a large feature vector, which will outweight the smalll(128 only) facenet features
• yes, you can predict a whole set of features, the RESULT mat will have 1 prediction row per sample. flags in this case should be probably 0, but RAW_OUTPUT (probability, not class result) would be an option

• your labels should be CvType.CV_32SC1, not CvType.CV_8UC1
• the yale db is grayscale, it's somewhat "unfair", trying with facenet here, which expects color images
• a 50/50 split is not good, bad here, given that the db is somewhat an ordered sequence of lighting conditions. please lookup, how "cross-validation" works, and rather use 5 or 10 fold CV.
• your BIF params will make a large feature vector, which will outweight the smalll(128 only) facenet features
• yes, you can predict a whole set of features, the RESULT mat will have 1 prediction row per sample. flags in this case should be probably 0, but RAW_OUTPUT (probability, not class result) would be an option

• your labels should be CvType.CV_32SC1, not CvType.CV_8UC1
• the yale db is grayscale, it's somewhat "unfair", trying with facenet here, which expects color images
• a 50/50 split is bad here, given that the db is somewhat an ordered sequence of lighting conditions. please lookup, how "cross-validation" works, and rather use 5 or 10 fold CV.
• your BIF params will make a large feature vector, which will outweight the smalll(128 only) facenet features
• yes, you can predict a whole set of features, the RESULT mat will have 1 prediction row per sample. flags in this case should be probably 0, but RAW_OUTPUT (probability, (probability (or rather, distance to the margin here), not class result) would be an optionoption)

• your labels should be CvType.CV_32SC1, not CvType.CV_8UC1
• the yale db is grayscale, it's somewhat "unfair", trying with facenet here, which expects color images
• a 50/50 split is bad here, given that the db is somewhat an ordered sequence of lighting conditions. please lookup, how "cross-validation" works, and rather use 5 or 10 fold CV.
• your BIF params will make a large feature vector, which will outweight the smalll(128 only) facenet features
• yes, you can predict a whole set of features, the RESULT mat will have 1 prediction row per sample. sample (but, - float, not integer!). flags in this case should be probably 0, but RAW_OUTPUT (probability (or rather, distance to the margin here), not class result) would be an option)

• your labels should be CvType.CV_32SC1, not CvType.CV_8UC1
• the yale db is grayscale, it's somewhat "unfair", trying with facenet here, which expects color imagesimages. (try with the lfw database instead ?)
• a 50/50 split is bad here, given that the db is somewhat an ordered sequence of lighting conditions. please lookup, how "cross-validation" works, and rather use 5 or 10 fold CV.
• your BIF params will make a large feature vector, which will outweight the smalll(128 only) facenet features
• yes, you can predict a whole set of features, the RESULT mat will have 1 prediction row per sample (but, - float, not integer!). flags in this case should be probably 0, but RAW_OUTPUT (probability (or rather, distance to the margin here), not class result) would be an option)