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
220
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
870
Lecture materials at the University of Tokyo School of Medicine
hoxomaxwell
1
150
Kaggle Hungry Geese
hoxomaxwell
1
110
HuBMAP 17th place model pipeline
hoxomaxwell
1
100
LT: Shallow Dive into Bayes Factor
hoxomaxwell
6
1.4k
Kaggle APTOS 2019 @ U-Tokyo Med
hoxomaxwell
1
420
Cornell Birdcall 36th place solution
hoxomaxwell
2
240
Kaggle Bengali.AI 6 th place solution
hoxomaxwell
4
8.7k
Google Colaboratory Shortcuts
hoxomaxwell
2
1k
Other Decks in Science
See All in Science
データマイニング - グラフ構造の諸指標
trycycle
PRO
0
200
[Paper Introduction] From Bytes to Ideas:Language Modeling with Autoregressive U-Nets
haruumiomoto
0
150
機械学習 - pandas入門
trycycle
PRO
0
330
会社でMLモデルを作るとは @電気通信大学 データアントレプレナーフェロープログラム
yuto16
1
300
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
0
140
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
rudorudo11
0
120
2025-06-11-ai_belgium
sofievl
1
170
06_浅井雄一郎_株式会社浅井農園代表取締役社長_紹介資料.pdf
sip3ristex
0
680
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
1k
SciPyDataJapan 2025
schwalbe10
0
270
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
1.8k
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
1k
Featured
See All Featured
jQuery: Nuts, Bolts and Bling
dougneiner
65
7.9k
Principles of Awesome APIs and How to Build Them.
keavy
127
17k
Java REST API Framework Comparison - PWX 2021
mraible
34
8.9k
Designing for humans not robots
tammielis
254
26k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.7k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
10
620
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
359
30k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.5k
Site-Speed That Sticks
csswizardry
13
920
What’s in a name? Adding method to the madness
productmarketing
PRO
24
3.7k
Music & Morning Musume
bryan
46
6.9k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.2k
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