Added TensorMNIST to speed up computation, minor fix in agem and mas #1229
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The main change of the PR is related to the default MNIST dataset, which is now called
TorchMNIST
. The dataset does not return a PIL image anymore but directly a Torch tensor.This speeds up computation of strategies like A-GEM which access dataset items multiple times. The main bottleneck is due to the
ToPIL
transformation present in the defaultMNIST
implementation (which requires a subsequentToTensor
transformation, thus increasing the total time).