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
120
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
470
Lecture materials at the University of Tokyo School of Medicine
hoxomaxwell
1
83
Kaggle Hungry Geese
hoxomaxwell
1
71
HuBMAP 17th place model pipeline
hoxomaxwell
1
63
LT: Shallow Dive into Bayes Factor
hoxomaxwell
6
1.2k
Kaggle APTOS 2019 @ U-Tokyo Med
hoxomaxwell
1
370
Cornell Birdcall 36th place solution
hoxomaxwell
2
200
Kaggle Bengali.AI 6 th place solution
hoxomaxwell
4
7.3k
Google Colaboratory Shortcuts
hoxomaxwell
2
960
Other Decks in Science
See All in Science
『データ可視化学入門』を PythonからRに翻訳した話
bob3bob3
1
360
ultraArmをモニター提供してもらった話
miura55
0
110
Machine Learning for Materials (Lecture 4)
aronwalsh
0
670
Pokemon Roughs
shoryuuken
0
370
スポーツメトリクス設計に対比較法を使いまくる / Sports metrics design using pairwise comparison method (spoana#14)
konakalab
1
710
A Theory of Scrum Team Effectiveness 〜『ゾンビスクラムサバイバルガイド』の裏側にある科学〜
bonotake
12
5.1k
Machine Learning for Materials (Lecture 7)
aronwalsh
0
730
SIGDIAL論文読み会: PGTask: Introducing the Task of Profile Generation from Dialogues
kaiyo3
0
100
AI Alignment: A Comprehensive Survey
s_ota
0
180
Non-Gaussian methods for causal discovery
sshimizu2006
0
180
History towards Universal Neural Network Potential for Material Discovery
matlantis
0
150
研究・教育・産学連携の循環の実践
sshimizu2006
0
220
Featured
See All Featured
Side Projects
sachag
451
41k
For a Future-Friendly Web
brad_frost
172
9k
Atom: Resistance is Futile
akmur
259
25k
Designing on Purpose - Digital PM Summit 2013
jponch
110
6.5k
Automating Front-end Workflow
addyosmani
1356
200k
No one is an island. Learnings from fostering a developers community.
thoeni
16
2.1k
The Straight Up "How To Draw Better" Workshop
denniskardys
227
130k
What the flash - Photography Introduction
edds
64
11k
Fantastic passwords and where to find them - at NoRuKo
philnash
37
2.5k
GraphQLの誤解/rethinking-graphql
sonatard
50
9.2k
Teambox: Starting and Learning
jrom
128
8.4k
The World Runs on Bad Software
bkeepers
PRO
61
6.7k
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