Can you please explain this normalization method? First, you normalize the original image and the flipped image. Then you sum both embeddings into one.
embds_arr = embds_arr/np.linalg.norm(embds_arr, axis=1, keepdims=True)+embds_f_arr/np.linalg.norm(embds_f_arr, axis=1, keepdims=True)
Why would this work at inference time? Can you explain why this is better than just running the embedding and then normalizing it?
Can you please explain this normalization method? First, you normalize the original image and the flipped image. Then you sum both embeddings into one.
embds_arr = embds_arr/np.linalg.norm(embds_arr, axis=1, keepdims=True)+embds_f_arr/np.linalg.norm(embds_f_arr, axis=1, keepdims=True)Why would this work at inference time? Can you explain why this is better than just running the embedding and then normalizing it?
Thanks