pytorch simple implement for the CVPR 2018 paper Dynamic Few Shot Visual Learning without Forgetting in jupyter version.
download the MiniImagenet dataset from here and modify the data root.
- Step 1 refers to pretrain Feature Extractor and cosine-based Classifier. In this process I set the epoch_num to 30.
- Step 2 refers to continue train Classifier and attention-based Few-shot Weight Generator.
- I get similar result as published in paper.
