ByteDance-Seed / ByteDance-Seed/Bagel

image edit训练数据格式

Open
#268 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
6.2k
Forks
545
PR merge metrics
No merged PRs in 30d

Description

请问在进行图像编辑任务的训练,是不是要求parquet中,每个训练样本的image和intruction list长度一样?我在自定义数据上进行训练,长度不一样时会出现数据读取失败的报错。
`Error index 2 is out of bounds for axis 0 with size 1 in rg#0,`

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the image-edit training failure with custom parquet data where the image and instruction lists have different lengths. Trace the data-reading path that produces the reported index-out-of-bounds error, then verify the expected sample format and confirm that valid inputs load successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.