Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel

README.md 803 B

You have to be logged in to leave a comment. Sign In

Pytorch Classification Pipeline

Default GPU: Apple-Silicon (m1-pro)

Dataset:

CUB200 Dataset: folder 001-020

Requirement Package:

  • torch
  • torchvision
  • dagshub
  • dvc
  • pandas

1. Config:

  • Customize CFG: configuration for train and test
  • Path: configuration for save and load files
  • Message: pre-defined debug / error message

2. Data Preprocess:

# python ./src/data_preprocess.py /path/to/data/root
python ./src/data_preprocess.py ./data
  • [default] unzip dataset.zip to ./data/images folder
  • [default] split train / test .csv file and save to ./data folder

3. Train Model:

python ./src/train.py --train_csv ./data/train.csv --test_csv ./data/test.csv
  • Support: ResNet18, ResNet34, ResNet50, ResNet101
  • [default] save final model to ./model folder
Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Loading...