search

facebookresearch / segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Apache License 2.0
47.76k stars 5.65k forks source link

How to use SA-1B #291

Open liuxy1103 opened 1 year ago

liuxy1103 commented 1 year ago

https://scontent-nrt1-1.xx.fbcdn.net/m1/v/t6/An8MNcSV8eixKBYJ2kyw6sfPh-J9U4tH2BV7uPzibNa0pu4uHi6fyXdlbADVO4nfvsWpTwR8B0usCARHTz33cBQNrC0kWZsD1MbBWjw.txt?ccb=10-5&oh=00_AfCyB7Icjme5eKJOWOHvK70QI6PTtWlk9symqgMGYyrWJQ&oe=646D7C98&_nc_sid=fb0754 I have download one of these links, but I wonder how to use this file with more than 10 GB. What's it data organization

lyc200522 commented 1 year ago

hello,Have you solved this problem yet

ryouchinsa commented 1 year ago

RectLabel is an offline image annotation tool for object detection and segmentation. Although this is not an open source program, you can drag & drop the COCO RLE JSON file of the SA-1B dataset to the labels table to import mask annotations.

Segment Anything 1 Billion (SA-1B) is a dataset designed for training general-purpose object segmentation models from open world images.

dragDropRLEJSONFilesXML

ryouchinsa commented 1 year ago

Improved "Create polygon using SAM" feature so that you can label pixels using the pixels option. You can label Segment Anything 1 Billion (SA-1B) like dataset by yourself.

sam-pixels