orobix / Prototypical-Networks-for-Few-shot-Learning-PyTorch

Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch
MIT License
986 stars 210 forks source link

How to train a new dataset? #24

Open mohammad-saber opened 4 years ago

mohammad-saber commented 4 years ago

Thank you very much for sharing your code.

I want to train models with a dataset other than miniImageNet and Omniglot. Could you guide me how to arrange dataset (main folder , sub-folder), and how to train models on a new dataset?

Thanks a lot.

qcy007 commented 4 years ago

Thank you very much for sharing your code.

I want to train models with a dataset other than miniImageNet and Omniglot. Could you guide me how to arrange dataset (main folder , sub-folder), and how to train models on a new dataset?

Thanks a lot.

Hi !Are you in the HUAWEI AI competition, too?

mohammad-saber commented 4 years ago

Thank you very much for sharing your code. I want to train models with a dataset other than miniImageNet and Omniglot. Could you guide me how to arrange dataset (main folder , sub-folder), and how to train models on a new dataset? Thanks a lot.

Hi !Are you in the HUAWEI AI competition, too?

Hi, No I didn't join the competition. I am personally interested in few shot learning.

yuchenlichuck commented 3 years ago

Same Problems too, I wanna train on more specificial dataset

pranay-ar commented 3 years ago

Hey, @mohammad-saber @yuchenlichuck, were you able to train this on a custom dataset and if you were successful in it, what did your results look like?

Dracula-funny commented 10 months ago

Hey, @mohammad-saber @yuchenlichuck, were you able to train this on a custom dataset and if you were successful in it, what did your results look like?

Hey,were you able to train this on a custom dataset and if you were successful in it, what did your results look like?