Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Great Barrier Reef Model Pipeline: 15th place
Search
Maxwell
February 16, 2022
Science
1
200
Great Barrier Reef Model Pipeline: 15th place
https://www.kaggle.com/c/tensorflow-great-barrier-reef
All I want to use was YOLO-X!
Maxwell
February 16, 2022
Tweet
Share
More Decks by Maxwell
See All by Maxwell
Causal Impact -paper summary-
hoxomaxwell
3
790
Lecture materials at the University of Tokyo School of Medicine
hoxomaxwell
1
130
Kaggle Hungry Geese
hoxomaxwell
1
100
HuBMAP 17th place model pipeline
hoxomaxwell
1
93
LT: Shallow Dive into Bayes Factor
hoxomaxwell
6
1.3k
Kaggle APTOS 2019 @ U-Tokyo Med
hoxomaxwell
1
420
Cornell Birdcall 36th place solution
hoxomaxwell
2
230
Kaggle Bengali.AI 6 th place solution
hoxomaxwell
4
8.4k
Google Colaboratory Shortcuts
hoxomaxwell
2
1k
Other Decks in Science
See All in Science
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
850
深層学習を用いた根菜類の個数カウントによる収量推定法の開発
kentaitakura
0
150
インフラだけではない MLOps の話 @事例でわかるMLOps 機械学習の成果をスケールさせる処方箋 発売記念
icoxfog417
PRO
2
830
[第62回 CV勉強会@関東] Long-CLIP: Unlocking the Long-Text Capability of CLIP / kantoCV 62th ECCV 2024
lychee1223
1
940
FRAM - 複雑な社会技術システムの理解と分析
__ymgc__
1
190
機械学習 - 授業概要
trycycle
PRO
0
190
データベース02: データベースの概念
trycycle
PRO
2
750
07_浮世満理子_アイディア高等学院学院長_一般社団法人全国心理業連合会代表理事_紹介資料.pdf
sip3ristex
0
470
安心・効率的な医療現場の実現へ ~オンプレAI & ノーコードワークフローで進める業務改革~
siyoo
0
230
CV_5_3dVision
hachama
0
140
「美は世界を救う」を心理学で実証したい~クラファンを通じた新しい研究方法
jimpe_hitsuwari
1
130
データマイニング - グラフデータと経路
trycycle
PRO
1
120
Featured
See All Featured
Rebuilding a faster, lazier Slack
samanthasiow
81
9k
A better future with KSS
kneath
239
17k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
52
2.8k
How STYLIGHT went responsive
nonsquared
100
5.6k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
16
920
Speed Design
sergeychernyshev
31
990
GraphQLとの向き合い方2022年版
quramy
46
14k
Agile that works and the tools we love
rasmusluckow
329
21k
Optimizing for Happiness
mojombo
379
70k
Mobile First: as difficult as doing things right
swwweet
223
9.7k
Transcript
Copyright 2022 Maxwell_110 Validation strategy - Sequence-based 4 fold CV
- The number of CoTS is close in each fold - Training data is frames with CoTs - Validation data includes frames w/o CoTs Resize up to 2.75 times using progressive learning 1280 720 Augmentation Increasing probability of applying augmentation as progressive learning progresses. - Default YOLO-X augmentations - random resize: (-5, 5) - mosaic / MixUp / hsv / flip: p = 0.6 -> 0.8 - degrees: Not used - translate: 0.1 - mosaic / MixUp scale: (0.5, 1.5) - RandomGamma - RGBShift - Sharpen - GaussNoise Batch Size: 4 GeForce RTX 3080 (x 2) Solution description in Kaggle discussion https://www.kaggle.com/c/tensorflow-great-barrier-reef/discussion/307691 Learning strategy - Progressive learning - Optimizer: default SGD (decay: 5e-4, momentum: 0.9) - LR: .000625 - Scheduler: yoloxwarmcos - min_lr_ratio: 0.1 - EMA: on - warmup_epochs: 5 - max_epoch: 30 TTA Seq-NMS https://arxiv.org/abs/1602.08465 https://github.com/tmoopenn/seq-nms n_frames: 2 confidence threshold: 0.07 linkage threshold: 0.1 nms th: 0.4 Weighted Box Fusion skip box threshold: 0.05 wbf IoU threshold: 0.45 Final confidence threshold: .08 Public LB : 0.607 Private LB : 0.714