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

Question

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

Opened this issue 4 years ago · 3 comments

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

Answer 1 · 2020-09-30T08:53:35.000Z

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.

Answer 2 · 2020-10-30T07:00:04.000Z

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?

Answer 3 · 2022-02-04T07:19:43.000Z

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