yangxue0827/FPN_Tensorflow

The problem for not fixing BN

Open

#21 建立於 2018年6月6日

在 GitHub 查看
 (6 留言) (0 反應) (0 負責人)Python (413 star) (150 fork)batch import
good first issue

描述

What is the Map in pascal voc 07 dataset using this code? As i read your code, i find that you do not fix the BN parameters. The batchsize is small, following the paper FPN or Mask RCNN, you need to set the training and trainbale to False for the slim.batch_norm op. I am testing whether this is the problem for the bad generalization for mutiple objects.

貢獻者指南

技術棧
pythontensorflow
領域
machine learning
議題類型
bug
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
half day
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
needs investigation
前置要求
TensorFlow basicsBatch normalization understandingObject detection with FPN
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
10
研究方向
Investigate the handling of batch normalization in the training code. Look at the model definition and training script to see if batch norm parameters are frozen. Check comments in the issue for discussion about small batch size and generalization. Possibly modify the training to set slim.batch norm training parameter to False as suggested.