Support for custom dataset

facebookresearch / suncet

Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803

MIT License

486 stars 67 forks source link

Support for custom dataset #14

Closed benedictflorance closed 3 years ago

benedictflorance commented 3 years ago

Does the repo have support for custom datasets? (Other than ImageNet/CIFAR10)

MidoAssran commented 3 years ago

Hi @benedictflorance,

To use a different dataset, you would just need to replace the init_data() function call in paws_train.py to return your custom dataloader/samplers instead.

Happy to help you debug if you run into any issues here.