DetectionTeamUCAS / DetectionTeamUCAS/Cascade_FPN_Tensorflow

Out of range error, when restore model

Open
#6 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
35
Forks
10
PR merge metrics
No merged PRs in 30d

Description

大佬您好,我之前跑了您的Faster Rcnn和Casecade的代码,现在尝试Casecade_FPN时遇到了Out of range的问题,我的数据集是voc格式的,也可以用convert_data_to_tfrecord.py和convert_data_to_tfrecord_voc2012.py进行数据转化,并且能够在tfrecord下生成文件。我看readme里您用的是coco数据集进行训练,请问我这个outofrange的报错是因为数据格式不匹配吗?因为这组数据在Faster和casecade上都可以训练,所以我排出了图片和label对应不准的问题。谢谢您!希望得到您的回复!

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.