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
840
Lecture materials at the University of Tokyo School of Medicine
hoxomaxwell
1
140
Kaggle Hungry Geese
hoxomaxwell
1
110
HuBMAP 17th place model pipeline
hoxomaxwell
1
98
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
地表面抽出の方法であるSMRFについて紹介
kentaitakura
1
870
データから見る勝敗の法則 / The principle of victory discovered by science (open lecture in NSSU)
konakalab
1
150
データマイニング - コミュニティ発見
trycycle
PRO
0
150
Trend Classification of InSAR Displacement Time Series Using SAE–CNN
satai
4
630
academist Prize 4期生 研究トーク延長戦!「美は世界を救う」っていうけど、どうやって?
jimpe_hitsuwari
0
160
点群ライブラリPDALをGoogleColabにて実行する方法の紹介
kentaitakura
1
400
CV_5_3dVision
hachama
0
150
01_篠原弘道_SIPガバニングボード座長_ポスコロSIPへの期待.pdf
sip3ristex
0
660
データベース01: データベースを使わない世界
trycycle
PRO
1
770
My Favourite Book in 2024: Get Rid of Your Japanese Accent
lagenorhynque
1
110
AIに仕事を奪われる 最初の医師たちへ
ikora128
0
970
「美は世界を救う」を心理学で実証したい~クラファンを通じた新しい研究方法
jimpe_hitsuwari
1
160
Featured
See All Featured
Large-scale JavaScript Application Architecture
addyosmani
512
110k
Facilitating Awesome Meetings
lara
55
6.5k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Faster Mobile Websites
deanohume
309
31k
Thoughts on Productivity
jonyablonski
70
4.8k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
36
2.5k
GitHub's CSS Performance
jonrohan
1032
460k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Designing Experiences People Love
moore
142
24k
How to Ace a Technical Interview
jacobian
279
23k
How STYLIGHT went responsive
nonsquared
100
5.8k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
131
19k
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