Skip to main content

PySodium

Project description

PySodium V0.0.1

Usage

  1. Install the PySodium Library

pip install git+https://github.com/satyajitghana/PySodium.git#egg=sodium

  1. Create a config.yml
name: CIFAR10_MyNet
save_dir: saved/
seed: 1
target_device: 0

arch:
    type: CIFAR10Model
    args: {}

augmentation:
    type: CIFAR10Transforms
    args: {}

data_loader:
    type: CIFAR10DataLoader
    args:
        batch_size: 64
        data_dir: data/
        nworkers: 4
        shuffle: True

criterion: cross_entropy_loss

lr_scheduler:
    type: OneCycleLR
    args:
        max_lr: 0.1

optimizer:
    type: SGD
    args:
        lr: 0.008
        momentum: 0.95

training:
    epochs: 50
  1. Run the Model !
# import my baby-library
from sodium.utils import load_config
import sodium.runner as runner

# create a runner
config = load_config('config.yml', tsai_mode=False)

# train the network
runner.train(config)

# plot metrics
runner.plot()

NOTE

if you are using the library on a terminal, you can use the main.py and call

python main.py --config=config.yml


Made with ❤ by shadowleaf.satyajit

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Built Distribution

py_sodium-0.0.2-py3-none-any.whl (20.0 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page