search

G-U-N / ECCV22-FOSTER

The official implementation for ECCV22 paper: "FOSTER: Feature Boosting and Compression for Class-Incremental Learning" in PyTorch.
MIT License
51 stars 4 forks source link

Imagenet100 dataset load #11

Closed WeiLeZhang closed 1 year ago

WeiLeZhang commented 1 year ago

Thank you for such a good work. May I ask if I want to run some experiments on imagenet100, is the path of the imagenet1K dataset entered here in the data.py file? image

G-U-N commented 1 year ago

Thank you for your interest!

To run experiments on Benchmark ImageNet-100, you should manually copy the data of 100 subcategories (provided as imagenet-sub in the repo) into an additional folder and then specify the path to the folder in data.py.

Hope this clarifies your queries.

WeiLeZhang commented 1 year ago

OK, Thank you!