search

Impression2805 / CVPR21_PASS

PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"
103 stars 20 forks source link

W #9

Open 2698022795 opened 1 year ago

2698022795 commented 1 year ago

Hello , I wonder why the code in train() function writing like this?

target = torch.stack([target * 4 + k for k in range(4)], 1).view(-1)

instead of using this

target = torch.stack([target * k for k in range(4)], 1).view(-1)