Lava-DL, but with PyTorch-Lightning flavour

Last update: Oct 31, 2022

Related tags

Deep Learning lava-dl-lightning

Overview

Deep learning project seed

Use this seed to start new deep learning / ML projects.

Built in setup.py
Built in requirements
Examples with MNIST
Badges
Bibtex

Goals

The goal of this seed is to structure ML paper-code the same so that work can easily be extended and replicated.

DELETE EVERYTHING ABOVE FOR YOUR PROJECT

Your Project Name

Description

What it does

How to run

Requires Python 3.8+. First, install dependencies

# clone project   
git clone https://github.com/Barchid/lava-dl-lightning
cd lava-dl-lightning

# install lava
wget https://github.com/lava-nc/lava/releases/download/v0.2.0/lava-nc-0.2.0.tar.gz
pip install -U pip
pip install lava-nc-0.2.0.tar.gz

# install lava-dl
wget https://github.com/lava-nc/lava-dl/releases/download/v0.1.1/lava-dl-0.1.1.tar.gz
pip install lava-dl-0.1.1.tar.gz

# install pytorch-lightning
pip install pytorch-lightning torchmetrics

Next, navigate to any file and run it.

# module folder
cd project

# run module (example: mnist as your main contribution)   
python lit_classifier_main.py

Imports

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

from project.datasets.mnist import mnist
from project.lit_classifier_main import LitClassifier
from pytorch_lightning import Trainer

# model
model = LitClassifier()

# data
train, val, test = mnist()

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

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

Citation

@article{YourName,
  title={Your Title},
  author={Your team},
  journal={Location},
  year={Year}
}

Lava-DL, but with PyTorch-Lightning flavour

Related tags

Overview

Deep learning project seed

Goals

DELETE EVERYTHING ABOVE FOR YOUR PROJECT

Your Project Name

Description

How to run

Imports

Citation

Owner

Sami BARCHID

Implementation of SETR model, Original paper: Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers.

Turi Create simplifies the development of custom machine learning models.

NeRF visualization library under construction

Indices Matter: Learning to Index for Deep Image Matting

ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees

An implementation of based on pytorch and mmcv

[ICLR2021] Unlearnable Examples: Making Personal Data Unexploitable

A Pytorch Implementation of [Source data‐free domain adaptation of object detector through domain

Optimizing Value-at-Risk and Conditional Value-at-Risk of Black Box Functions with Lacing Values (LV)

STEM: An approach to Multi-source Domain Adaptation with Guarantees

Image-to-image translation with conditional adversarial nets

Code for the paper: Hierarchical Reinforcement Learning With Timed Subgoals, published at NeurIPS 2021

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

vit for few-shot classification

Reimplement of SimSwap training code

Language-Agnostic Website Embedding and Classification

DeepVoxels is an object-specific, persistent 3D feature embedding.

Code and dataset for ACL2018 paper "Exploiting Document Knowledge for Aspect-level Sentiment Classification"

training script for space time memory network

This is the official implementation of 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection, built on SECOND.