search

ZhaoJ9014 / face.evoLVe

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
MIT License
3.44k stars 760 forks source link

extract_feature_v1.py. I think there is a missing l2_norm in line 75. #23

Closed educob closed 5 years ago

educob commented 5 years ago

Hi.

while idx + batch_size <= len(loader.dataset):
            batch, _ = iter(loader).next()
            if tta:
                fliped = hflip_batch(batch)
                emb_batch = backbone(batch.to(device)).cpu() + backbone(fliped.to(device)).cpu()
                features[idx:idx + batch_size] = l2_norm(emb_batch)
            else:
      75:          features[idx:idx + batch_size] = backbone(batch.to(device)).cpu()
            idx += batch_size

        if idx < len(loader.dataset):
            batch, _ = iter(loader).next()
            if tta:
                fliped = hflip_batch(batch)
                emb_batch = backbone(batch.to(device)).cpu() + backbone(fliped.to(device)).cpu()
                features[idx:] = l2_norm(emb_batch)
            else:
                features[idx:] = l2_norm(backbone(batch.to(device)).cpu())

Line 75 seems to have missing l2_norm as the other 3 cases have.

I'd thank an explanation why l2_norm is necessary. If the aim is to search in the database who that person is, normalizing doesn't seem a good idea.

Thanks.

ZhaoJ9014 commented 5 years ago

Hi.

while idx + batch_size <= len(loader.dataset):
            batch, _ = iter(loader).next()
            if tta:
                fliped = hflip_batch(batch)
                emb_batch = backbone(batch.to(device)).cpu() + backbone(fliped.to(device)).cpu()
                features[idx:idx + batch_size] = l2_norm(emb_batch)
            else:
      75:          features[idx:idx + batch_size] = backbone(batch.to(device)).cpu()
            idx += batch_size

        if idx < len(loader.dataset):
            batch, _ = iter(loader).next()
            if tta:
                fliped = hflip_batch(batch)
                emb_batch = backbone(batch.to(device)).cpu() + backbone(fliped.to(device)).cpu()
                features[idx:] = l2_norm(emb_batch)
            else:
                features[idx:] = l2_norm(backbone(batch.to(device)).cpu())

Line 75 seems to have missing l2_norm as the other 3 cases have.

I'd thank an explanation why l2_norm is necessary. If the aim is to search in the database who that person is, normalizing doesn't seem a good idea.

Thanks.

Thank you. We have updated accordingly:)