Open shinji-ohkubo opened 3 years ago
multibox_loss.py -->num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
If positive is 0, negative is also 0, which hinders negative learning and causes over-detection. I think it is correct to set a fixed minimum value.
multibox_loss.py -->num_neg = torch.clamp(self.negpos_ratio * num_pos, max=pos.size(1) - 1)
If positive is 0, negative is also 0, which hinders negative learning and causes over-detection. I think it is correct to set a fixed minimum value.