facebookresearch / facebookresearch/moco

What is the label format of the cifar-10 dataset?

Open
#138 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
No language data
Stars
5.1k
Forks
802
PR merge metrics
No merged PRs in 30d

Description

Hello,
I tried to modify the cifar-10 image dataset into the ECG dataset MIT through the official moco demo code to do the transfer learning of comparative learning.
My current problem is that the moco demo is a packaged cifar10 dataset library that is directly imported. I need to upload the MIT dataset locally, but I don’t know what format the label file of the packaged cifar-10 dataset library is in, because The code provided by the demo only uses data, so I can only get the format of the data but not the format of the label file of the cifar-10 dataset. I have saved the ecg data and labels of the MIT dataset into two .npy arrays, and made corresponding modifications according to the data format in the demo, but I don't know what format the label file of the original cifar-10 dataset should be?
Could someone please help me solve this problem and tell me what is the format of the label of the demo packaged cifar-10 dataset library? Looking forward to it and thank you for your help!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.