Jonna Matthiesen

icon company Embedl AB icon location Deep Learning Researcher @ Embedl | Hardware-Aware Model Optimization - NAS - Pruning - Quantization

Results 3 issues of Jonna Matthiesen

update mean and std of cifar dataset

1 comment

The previous normalization values for CIFAR-10 seem to be wrong. Source: [Correct Normalization Values for CIFAR-10](https://github.com/kuangliu/pytorch-cifar/issues/19#issue-268972488) The given models need to be re-run to get updated results (performance).

Feature/lr milestones

**Add parser argument to set LR milestone for training** When training with a different number of total epochs it makes sense to adjust the LR schedule. See my comment: [About...

Adding more flags to main.py

Hi, I would like to contribute and make `main.py` a proper training script. Adding, for example, ``` if __name__ == "__main__": main() ``` and restructuring the code accordingly. and some...