matkowski-voy comments

Repositories
Issues
Comments

Results 3 comments of


                                            matkowski-voy

LwF gradient backpropagation

another thing is whether the `self.prev_model` should be `.train()` or `.eval()` because currently it is in the training mode so it would affect batch norm and dropouts for example and...

Memory Replay increased GPU memory consumption after the first experience

The code is attached below. There are 2 experiences in the data stream scenario (```generic_scenario = dataset_benchmark([trainset1, trainset2], [testset1, testset2])```) and - during first experience the GPU memory usage is...

Memory Replay increased GPU memory consumption after the first experience

Hi @HamedHemati , yes, that solves the issue. Thanks a lot! :)