yangxue0827/FPN_Tensorflow

The problem for not fixing BN

Open

#21 opened on Jun 6, 2018

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (150 forks)batch import
good first issue

Repository metrics

Stars
 (413 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

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.

Contributor guide

Research direction
Investigate the implementation of batch normalization layers in the FPN code. Check if the BN layers are set to trainable=False during training and if the moving statistics are updated correctly. Compare with the original FPN paper recommendations.
Tech stack
pythontensorflow
Domain
backendmachine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
PythonTensorFlowGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35