Penulis: admin

Model Smoothness Can Predict Intra Domain and Out of Domain Generalization

Paper: Predicting Out-of-Domain Generalization with Local Manifold Smoothness

Code: none yet

You Only Look Once (YOLO) Object Detection Models

YOLOv1

Code

Paper: JOseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, “You Only Look Once: Unified, Real-Time Object Detection“, 2016

Code: https://github.com/AlexeyAB/darknet

YOLOv2

Paper: “YOLO9000:Better, Faster, Stronger“

Code: https://pjreddie.com/darknet/yolov2/

YOLOv3

Paper: YOLOv3: An Incremental Improvement

Code: https://pjreddie.com/darknet/yolo/

YOLOv4

Paper:

Code:

YOLOv5

Paper: none yet

Code: https://github.com/ultralytics/yolov5

YOLOv6

Paper: none yet

Code: https://github.com/meituan/YOLOv6

YOLOv7

Official YOLOv7 (state-of-the-art real-time detector) is more accurate and faster than:

  • – YOLOv5 by 120% FPS
  • – YOLOX by 180% FPS
  • – Dual-Swin-T by 1200% FPS
  • – ConvNext by 550% FPS
  • – SWIN-L CM-RCNN by 500% FPS
  • – PPYOLOE-X by 150% FPS

Paper: Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, 2022

Code: https://github.com/WongKinYiu/yolov7/releases

References

  • A Brief History of YOLO Object Detection Models From YOLOv1 to YOLOv5

Replikasi Solusi Kompetisi Global Wheat Challenge 2021

Pada artikel ini dibahas usaha untuk mereplikasi solusi dari GWC_solution

Hardware yang dipakai: RTX 3090

Catatan

  • RTX3090 tidak kompatibel dengan Cuda 10.2 , minimal perlu CUDA 11.3
  • PyTorch 1.9.0 tidak kompatibel dengan CUDA 11.3, sehingga perlu diganti dengan PyTorch 1.10.0
  • Script GWC_YOLOv5 tidak kompatibel dengan PyTorch 1.12.0

Prosedur

Create Conda environment

conda create --name gwc8 python=3.7.10 scipy=1.4.
conda activate gwc8

Install PyTorch

pip3 install torch==1.10.0 torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113

Install prerequisites

pip install -r requirements.txt
pip install numpy==1.19.5
pip uninstall -y PyYAML
pip install PyYAML==5.3.1
pip install ensemble_boxes
pip install setuptools==59.5.0
pip install jupyter
pip install matplotlib
pip install opencv-python
pip install tensorboard

Clone GWC_solution

cd /home/admin
git clone https://github.com/ksnxr/GWC_solution.git

Clone GWC_YOLOv5

cd GWC_solution
git clone https://github.com/ksnxr/GWC_YOLOv5.git

Jalankan jupyter notebook


jupyter notebook --allow-root --no-browser --ip=0.0.0.0

Setelah itu buka jupyter notebook dari browser

Eksekusi script berikut

Training

python train.py --name 4fold0 --img 800 --batch 8 --epochs 35 --data custom.yaml --weights yolov5x.pt --cache-images --save_period 1

Monitor training

cd /home/admin/GWC_solution/GWC_YOLOv5
tensorboard --logdir runs/train  --bind_all

Berikut ini data flow diagram dari proses komputasi

Referensi

Ethereum Merge

Update: March 24,2022

Ethereum
The Merge

Eventually the current Ethereum Mainnet will "merge" with the beacon chain proof-of-stake system.
This will mark the end of proof-of-work for Ethereum, and the full transition to proof-of-stake.
This is planned to precede the roll out of shard chains.
We formerly referred to this as "the docking."
This upgrade represents the official switch to proof-of-stake consensus. This eliminates the need for energy-intensive mining, and instead secures the network using staked ether. A truly exciting step in realizing the Ethereum vision – more scalability, security, and sustainability.

Reference: https://ethereum.org/en/upgrades/merge/

ICEYE Free Dataset

This data is collected by the world’s largest SAR satellite constellation. Ready to take a dive in the data? You can use it in research, and get an understanding of what radar satellite data can offer you. Download your free dataset (instant access): https://hubs.ly/Q0168WYZ0

Reference: https://twitter.com/iceyefi/status/1504369483913256962

Downloaded file: ICEYE_Strip_Example_SAR_Dataset_Singapore_Strait_12_2021.zip (size: 2.74 GB)

ICEYE also offers other datasets