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
210
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
メール送信サーバの集約における透過型SMTP プロキシの定量評価 / Quantitative Evaluation of Transparent SMTP Proxy in Email Sending Server Aggregation
linyows
0
930
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
680
ウェブ・ソーシャルメディア論文読み会 第25回: Differences in misinformation sharing can lead to politically asymmetric sanctions (Nature, 2024)
hkefka385
0
110
Quelles valorisations des logiciels vers le monde socio-économique dans un contexte de Science Ouverte ?
bluehats
1
390
03_草原和博_広島大学大学院人間社会科学研究科教授_デジタル_シティズンシップシティで_新たな_学び__をつくる.pdf
sip3ristex
0
470
生成AIと学ぶPythonデータ分析再入門-Pythonによるクラスタリング・可視化をサクサク実施-
datascientistsociety
PRO
4
1.6k
データベース10: 拡張実体関連モデル
trycycle
PRO
0
690
Healthcare Innovation through Business Entrepreneurship
clintwinters
0
230
オンプレミス環境にKubernetesを構築する
koukimiura
0
260
データベース02: データベースの概念
trycycle
PRO
2
750
baseballrによるMLBデータの抽出と階層ベイズモデルによる打率の推定 / TokyoR118
dropout009
1
420
データベース08: 実体関連モデルとは?
trycycle
PRO
0
670
Featured
See All Featured
RailsConf 2023
tenderlove
30
1.1k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
700
The World Runs on Bad Software
bkeepers
PRO
69
11k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
Bash Introduction
62gerente
614
210k
Code Review Best Practice
trishagee
68
18k
Building an army of robots
kneath
306
45k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
357
30k
Why You Should Never Use an ORM
jnunemaker
PRO
56
9.4k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
What's in a price? How to price your products and services
michaelherold
246
12k
Testing 201, or: Great Expectations
jmmastey
42
7.5k
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