Closed iperov closed 5 years ago
@polarisZhao can you please retrain your model with wider variations of scale/rotations/shift,
also add channels shuffling
rnd_state = np.random.RandomState (sample_rnd_seed)
img = np.take (img_bgr, rnd_state.permutation(img_bgr.shape[-1]), axis=-1)
and add random gaussian blur and motion blur
Thanks for your advice, I will add more data augmentation to retain this model.
U can use updeted checkpoint, the landmark will be better, Look forward to your feedback