How to reproduce the results on CIFAR10 and CIFAR100?
SodaCoder opened this issue · comments
Hello All,
This is Sourav Das, currently working as a Project-Linked Person at Indian Statistical Institute, Kolkata.
I went through your CVPR 2020 paper, titled "M2m: Imbalanced Classification via Major-to-minor Translation" and would like to reproduce the result on CIFAR10 and CIFAR100 datasets.
I cloned the GitHub repo https://github.com/alinlab/M2m but I don't know
- In which path to keep the CIFAR10 or CIFAR100 datasets?
- In which format should the datasets be present?
- Will it run with CIFAR10 and CIFAR100 datasets, directly downloaded from the site: https://www.cs.toronto.edu/~kriz/cifar.html or do I need to do some pre-processing to the datasets?
Awaiting an early response from you.
Thanks & Regards,
Sourav Das
Hi, Sourav. Thanks for the interest in our work! Answers to the questions are as follow:
- As you can see "get_imbalanced" function in data_loader.py, which is mainly used in our code for constructing data loader,
we load datasets in the location of DATA_ROOT. It is currently set to "~/data" (see line18). It can be changed to any directory as you want
2 & 3. Our codes are based on pytorch and torchvision, including the part for the construction of datasets. So, please check the details about it on the corresponding page. (https://pytorch.org/docs/1.1.0/torchvision/datasets.html?highlight=cifar)