- Python >= 3.7 (Recommend to use Anaconda or Miniconda)
- PyTorch >= 1.3
- NVIDIA GPU + CUDA
-
Clone repo
git clone https://github.com/moukamisama/FS-IL.git
-
Install dependent packages
cd FS-IL pip install -r requirements.txt -
Install wandb (optional)
Note that FS-IL is only tested in Ubuntu, and may be not suitable for Windows. You may try Windows WSL with CUDA supports :-) (It is now only available for insider build with Fast ring).
- Training and incremental testing commands: Please see TrainTest.md for the basic usage.
We evaluate our system in several datasets, including CUB-200-2011, CIFAR100, miniImageNet.
Please download CUB-200-2011, CIFAR100 and miniImageNet.(Note: some datasets do not split the train set and test set in the original folder, the splited datasets can be download from this link according to the original provided train/test text file.)