Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel
Task:  image classification Framework:  pytorch Integration:  dvc git
timho d41187c906
remove metrics and params from train pipeline output, retrain model again
2 years ago
04fe2cd0e0
Initialize DVC
2 years ago
ceb00cde7a
creat train pipeline and train new model
2 years ago
ceb00cde7a
creat train pipeline and train new model
2 years ago
src
46b71109e8
fix bug: set seed in config for data_preprocess
2 years ago
04fe2cd0e0
Initialize DVC
2 years ago
d41187c906
remove metrics and params from train pipeline output, retrain model again
2 years ago
92a8d8b5dc
update README.md
2 years ago
d41187c906
remove metrics and params from train pipeline output, retrain model again
2 years ago
d41187c906
remove metrics and params from train pipeline output, retrain model again
2 years ago
d41187c906
remove metrics and params from train pipeline output, retrain model again
2 years ago
98a05e0754
reproduce pipeline with data seed 20221026, update csv file and model
2 years ago
d41187c906
remove metrics and params from train pipeline output, retrain model again
2 years ago
8af84f59df
Add requirements, src, README to Git tracking
2 years ago
Storage Buckets
Data Pipeline
Legend
DVC Managed File
Git Managed File
Metric
Stage File
External File

README.md

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

About

Example for image classification in PyTorch framework

Collaborators 1

Comments

Loading...