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
MoveItを使った産業用ロボット向け動作作成方法の紹介 / Introduction to creating motion for industrial robots using MoveIt
ry0_ka
0
490
ガウス過程回帰とベイズ最適化
nearme_tech
PRO
1
430
Trend Classification of InSAR Displacement Time Series Using SAE–CNN
satai
3
450
データベース03: 関係データモデル
trycycle
PRO
1
120
3次元点群を利用した植物の葉の自動セグメンテーションについて
kentaitakura
2
1.2k
生成検索エンジン最適化に関する研究の紹介
ynakano
2
1k
学術講演会中央大学学員会府中支部
tagtag
0
270
動的トリートメント・レジームを推定するDynTxRegimeパッケージ
saltcooky12
0
140
機械学習 - DBSCAN
trycycle
PRO
0
890
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
850
局所保存性・相似変換対称性を満たす機械学習モデルによる数値流体力学
yellowshippo
1
280
Factorized Diffusion: Perceptual Illusions by Noise Decomposition
tomoaki0705
0
390
Featured
See All Featured
How to Ace a Technical Interview
jacobian
277
23k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
20
1.3k
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.5k
Statistics for Hackers
jakevdp
799
220k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
46
9.6k
Into the Great Unknown - MozCon
thekraken
39
1.9k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
10
930
Art, The Web, and Tiny UX
lynnandtonic
299
21k
Music & Morning Musume
bryan
46
6.6k
Build The Right Thing And Hit Your Dates
maggiecrowley
36
2.8k
It's Worth the Effort
3n
185
28k
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