Ensemble-Pytorch icon indicating copy to clipboard operation
Ensemble-Pytorch copied to clipboard

A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.

Results 36 Ensemble-Pytorch issues
Sort by recently updated
recently updated
newest added

hi @xuyxu, I've been taking a look at Voting.py, If I'm not mistaken, only soft voting is implemented. are there any plans for implementing majority/hard, plurality and weighted voting as...

new feature

This scheduler doesn't have this attributte because it doesn't inherit from `_LRScheduler`, and simply implementes the generic 'object' class. Instead of getting the leanring rate with `get_last_lr`, we could fetch...

bug

Have a 2 neural nets N1, N2, want to stack their output embedding layer. How to do this ?

Suspended since python 3.10 is not supported by GitHub CI for now.

Hi, I want to use Ensemble-PyTorch with PyTorch-Geometric. However, it doesn't recognize the dataloaders. Is this under development or a bug.

enhancement

Hu everyone, I am trying to script the ensemble, however, argsvar cannot be used with torchscript torch.jit.frontend.NotSupportedError: Compiled functions can't take variable number of arguments or use keyword-only arguments with...

new feature

Hi, Thank you for this super useful library. I've noticed that the ensemble modules are all restricted to either cross-entropy loss (in the case of classification) or mean squared error...

new feature