Learning With Retrospection

Description

Unofficial implementation of learning on top of PytorchLightning.

How to run

First, install dependencies

# clone project   
git clone https://github.com/mrifkikurniawan/LearningWithRetrospection.git

# install project   
cd LearningWithRetrospection 
pip install -e .   

Next, navigate to any file and run it.

# run training module (example: train lwr on mnist dataset)   
python train.py --cfg config/lwr_mnist_resnet18.yaml  

Imports

This project is setup as a package which means you can now easily import any file into any other file like so:

from lwr.trainer import LWR
from pytorch_lightning import Trainer

# model
model = LWR()

# data
train, val, test = mnist()

# train
trainer = Trainer()
trainer.fit(model, train, val)

# test using the best model!
trainer.test(test_dataloaders=test)

Experiments Results

To Do