Pretrained models
VigneshSrinivasan10 opened this issue · 3 comments
Dear Authors,
Thank you very much for the amazing work and the code!
It would be great if you could upload the pretrained models for Image classification tasks.
Thank you in advance,
@VigneshSrinivasan10
Thank you for your suggestion!
We will upload the pertained models. Please be patient as it takes time to prepare.
@kazukiosawa
Thank you very much for your reply.
In the meantime, I trained a model on CIFAR10 dataset as described in your repository. These are the results after training the model with configs/cifar10/lenet_vogn.json setting for 100 epochs. And these are the results I get:
Eval: Average loss: 1.8339, Accuracy: 6904/10000 (69.04%)
I find that the config file: configs/cifar10/lenet_vogn.json corresponds to VOGN+BN. However, I would like to reproduce the results from the paper of the setting VOGN+momentum+BN, where you get the best results.
It would be great if you update the config file to be compatible with that setting or point me in the direction of how to do it.
Thanks!
Dear authors,
I would like to know if it is still possible to get the pretrained weights ?