[PyTorch] DataLoader 이해하기 — Part 2

Theme : SimCLR

A simple framework for contrastive learning of visual representation

Dataset Wrapper

1. get_data_loaders

Train & Valid loader

2. _get_simclr_pipeline_transform

Train & Valid loader — Stochastic augmentation

3. SimCLRDataTransform

Return two different augmentation pipeline

4. get_train_validation_data_loaders

Train & Valid loader — Get mini-batches by using DataLoader

Tensor structure

Tensor structure for train_loader

Torchvision — datasets.STL10

1. Unlabeled dataset 일 것

torchvision.datasets.STL10 - return labels

2. Binary 형식이 아닌 일반적인 이미지 파일의 확장자를 지원할 것

Customizing Dataset Wrapper

Datapath list & MyDataset class
New ‘get_data_loaders’

--

--

AI researcher at Promedius Inc. Especially interested in theoretical physics, mathematics and deep learning.

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store