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
180
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
710
Lecture materials at the University of Tokyo School of Medicine
hoxomaxwell
1
120
Kaggle Hungry Geese
hoxomaxwell
1
91
HuBMAP 17th place model pipeline
hoxomaxwell
1
78
LT: Shallow Dive into Bayes Factor
hoxomaxwell
6
1.3k
Kaggle APTOS 2019 @ U-Tokyo Med
hoxomaxwell
1
410
Cornell Birdcall 36th place solution
hoxomaxwell
2
220
Kaggle Bengali.AI 6 th place solution
hoxomaxwell
4
8.3k
Google Colaboratory Shortcuts
hoxomaxwell
2
1k
Other Decks in Science
See All in Science
Factorized Diffusion: Perceptual Illusions by Noise Decomposition
tomoaki0705
0
340
【健康&筋肉と生産性向上の関連性】 【Google Cloudを企業で運用する際の知識】 をお届け
yasumuusan
0
470
Transformers are Universal in Context Learners
gpeyre
0
720
20分で分かる Human-in-the-Loop 機械学習におけるアノテーションとヒューマンコンピューターインタラクションの真髄
hurutoriya
5
2.8k
白金鉱業Meetup Vol.16_数理最適化案件のはじめかた・すすめかた
brainpadpr
3
1.4k
Celebrate UTIG: Staff and Student Awards 2024
utig
0
590
ウェーブレットおきもち講座
aikiriao
1
820
サイゼミ用因果推論
lw
1
3.4k
Introduction to Image Processing: 2.Frequ
hachama
0
480
The Incredible Machine: Developer Productivity and the Impact of AI
tomzimmermann
0
550
Analysis-Ready Cloud-Optimized Data for your community and the entire world with Pangeo-Forge
jbusecke
0
130
事業会社における 機械学習・推薦システム技術の活用事例と必要な能力 / ml-recsys-in-layerx-wantedly-2024
yuya4
4
300
Featured
See All Featured
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
251
21k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
33
2.8k
Building Better People: How to give real-time feedback that sticks.
wjessup
367
19k
Optimising Largest Contentful Paint
csswizardry
34
3.1k
Side Projects
sachag
452
42k
Stop Working from a Prison Cell
hatefulcrawdad
267
20k
The Cost Of JavaScript in 2023
addyosmani
47
7.4k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
27
1.9k
The Art of Programming - Codeland 2020
erikaheidi
53
13k
Automating Front-end Workflow
addyosmani
1368
200k
Measuring & Analyzing Core Web Vitals
bluesmoon
6
260
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
46
2.3k
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