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
8.6k
Google Colaboratory Shortcuts
hoxomaxwell
2
1k
Other Decks in Science
See All in Science
Symfony Console Facelift
chalasr
2
480
生成検索エンジン最適化に関する研究の紹介
ynakano
2
1.4k
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
tagtag
1
150
機械学習 - 授業概要
trycycle
PRO
0
250
KH Coderチュートリアル(スライド版)
koichih
1
48k
知能とはなにかーヒトとAIのあいだー
tagtag
0
100
地質研究者が苦労しながら運用する情報公開システムの実例
naito2000
0
290
ランサムウェア対策にも考慮したVMware、Hyper-V、Azure、AWS間のリアルタイムレプリケーション「Zerto」を徹底解説
climbteam
0
140
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
tagtag
0
110
SciPyDataJapan 2025
schwalbe10
0
270
Ignite の1年間の軌跡
ktombow
0
160
NASの容量不足のお悩み解決!災害対策も兼ねた「Wasabi Cloud NAS」はここがスゴイ
climbteam
1
170
Featured
See All Featured
Learning to Love Humans: Emotional Interface Design
aarron
274
41k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
55
3k
Optimising Largest Contentful Paint
csswizardry
37
3.5k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
23
1.5k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
253
22k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
37
2.6k
Faster Mobile Websites
deanohume
310
31k
The Pragmatic Product Professional
lauravandoore
36
6.9k
A better future with KSS
kneath
239
18k
4 Signs Your Business is Dying
shpigford
185
22k
The Language of Interfaces
destraynor
162
25k
Mobile First: as difficult as doing things right
swwweet
225
10k
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