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
160
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
2
600
Lecture materials at the University of Tokyo School of Medicine
hoxomaxwell
1
110
Kaggle Hungry Geese
hoxomaxwell
1
84
HuBMAP 17th place model pipeline
hoxomaxwell
1
69
LT: Shallow Dive into Bayes Factor
hoxomaxwell
6
1.2k
Kaggle APTOS 2019 @ U-Tokyo Med
hoxomaxwell
1
400
Cornell Birdcall 36th place solution
hoxomaxwell
2
210
Kaggle Bengali.AI 6 th place solution
hoxomaxwell
4
8k
Google Colaboratory Shortcuts
hoxomaxwell
2
980
Other Decks in Science
See All in Science
はじめてのバックドア基準:あるいは、重回帰分析の偏回帰係数を因果効果の推定値として解釈してよいのか問題
takehikoihayashi
2
730
Sarcoptic Mange
uni_of_nomi
1
110
Machine Learning for Materials (Lecture 6)
aronwalsh
0
510
DEIM2024 チュートリアル ~AWSで生成AIのRAGを使ったチャットボットを作ってみよう~
yamahiro
3
1.3k
第61回コンピュータビジョン勉強会「BioCLIP: A Vision Foundation Model for the Tree of Life」
x_ttyszk
1
1.5k
Snowflakeによる統合バイオインフォマティクス
ktatsuya
0
490
理論計算機科学における 数学の応用: 擬似ランダムネス
nobushimi
1
340
トラブルがあったコンペに学ぶデータ分析
tereka114
2
900
Machine Learning for Materials (Lecture 7)
aronwalsh
0
810
はじめての「相関と因果とエビデンス」入門:“動機づけられた推論” に抗うために
takehikoihayashi
17
6.8k
非同期コミュニケーションの構造 -チャットツールを用いた組織における情報の流れの設計について-
koisono
0
140
AI科学の何が“哲学”の問題になるのか ~問いマッピングの試み~
rmaruy
1
2.2k
Featured
See All Featured
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
4
370
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Why You Should Never Use an ORM
jnunemaker
PRO
54
9.1k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
26
2.1k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
28
2k
Fashionably flexible responsive web design (full day workshop)
malarkey
405
65k
No one is an island. Learnings from fostering a developers community.
thoeni
19
3k
StorybookのUI Testing Handbookを読んだ
zakiyama
27
5.3k
Happy Clients
brianwarren
98
6.7k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
47
5k
Gamification - CAS2011
davidbonilla
80
5k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
33
1.9k
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