search

yulu0724 / SDC-IL

Semantic Drift Compensation for Class-Incremental Learning (CVPR2020)
115 stars 34 forks source link

Could you please provide more run_demo.sh about other datasets？ #8

Open wusuoweima opened 3 years ago

wusuoweima commented 3 years ago

Could you please provide more run_demo.sh about other datasets（CUB-200-2011, Flowers-102, Caltech-101, ImageNet-Subset） ? @yulu0724

yulu0724 commented 3 years ago

We use lr 1e-6, 50 epochs for CUB-200-2011 (100 classes) and Caltech-101 (Fig.6). The parameters of other datasets are shown in 'Implementation Details' part of the paper.

pratikm141 commented 3 years ago

Which 100 classes do you choose for CUB-200? First 100? For CUB-200 and Caltech do you pre-train on the first task? For Caltech do you pre-train on Imagenet?

yulu0724 commented 2 years ago

We follow the LwM paper and use the first 100 for CUB-200 in Fig6. For CUB and Caltech we use the pretrained Imagenet.