PingoLH / CenterNet-HarDNet

Object detection achieving 44.3 mAP / 45 fps on COCO dataset
MIT License
169 stars 32 forks source link

How to derive the eigenvalue and eigenvector when perfor color transform? #12

Open sudo-rm-covid19 opened 3 years ago

sudo-rm-covid19 commented 3 years ago

Hi, As the title suggested, how to derive the following vector and matrix?

self._eig_val = np.array([0.2141788, 0.01817699, 0.00341571], dtype=np.float32) self._eig_vec = np.array([ [-0.58752847, -0.69563484, 0.41340352], [-0.5832747, 0.00994535, -0.81221408], [-0.56089297, 0.71832671, 0.41158938] ], dtype=np.float32)

Thanks in advance.