Open sheirving opened 1 year ago
https://github.com/lsabrinax/VideoTextSCM/blob/d87ad1bbb6ada7573a02a82045ee1b9ead5861ad/train_embedding.py#L47
Thankyou for share the code! But what's the mean of 'W_scale' in spatical_triplet_loss, and loss_pos = pos_dist * (W_scale + W_pos_dis) - alpha1, why we need to add 'w_scale'?
https://github.com/lsabrinax/VideoTextSCM/blob/d87ad1bbb6ada7573a02a82045ee1b9ead5861ad/train_embedding.py#L47
Thankyou for share the code! But what's the mean of 'W_scale' in spatical_triplet_loss, and loss_pos = pos_dist * (W_scale + W_pos_dis) - alpha1, why we need to add 'w_scale'?