PaddlePaddle/PaddleDetection

PAFNet训练loss难以下降

Open

#4,521 opened on Nov 9, 2021

View on GitHub
 (5 comments) (0 reactions) (1 assignee)Python (2,731 forks)batch import
help wantedtraining

Repository metrics

Stars
 (11,414 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

在自己的实验过程中更换了PAFNet的Backbone进行相关实验，由于此前没有使用dcn_head导致精度可能还是存在差距，所以在近期使用CSPDarknet+dcn_head的配置进行实验，但是发现在实验过程中模型的loss难以下降，使用COCO数据集跑了12个epoch后可以说是什么也没检测到，这是因为DCN的问题所导致的吗？ image

Contributor guide

Research direction
Investigate if Deformable Convolution (DCN) in the head causes unstable gradients or improper initialization in PAFNet with CSPDarknet backbone. Check DCN configuration, learning rate, and loss scaling.
Tech stack
python
Domain
backend
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
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.
Mostly clear
Prerequisites
Pythondeep learning basicsobject detection
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60