Skip to main content

LambdaResNet implementation in TensorFlow 2.2

Project description

LambdaResNet - TensorFlow

All credit goes to lucidrains for sharing the initial pytorch implementation. This repo takes majority of contents from his original repo here.

Implementation of λ-ResNet.

Yannic Kilcher's paper review

Install

$ pip install tf-lambda-resnet

Usage

LambdaResNet uses localized context as explained in the video.

import tensorflow as tf
from tf_lambda_resnet import LambdaResnet18

model = LambdaResnet18()
out = model(tf.ones([10, 224, 224, 3]))
print(out)

Credits

All the code is taken from the below resources. I have assembled them in a proper manner to make it work for TF2.2

References

Thanks to PistonY for sharing a gist here - lambda_net.py

Citations

@inproceedings{
    anonymous2021lambdanetworks,
    title={LambdaNetworks: Modeling long-range Interactions without Attention},
    author={Anonymous},
    booktitle={Submitted to International Conference on Learning Representations},
    year={2021},
    url={https://openreview.net/forum?id=xTJEN-ggl1b},
    note={under review}
}

Project details


Download files

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

Source Distribution

tf-lambda-resnet-0.1.4.tar.gz (4.6 kB view hashes)

Uploaded Source

Built Distribution

tf_lambda_resnet-0.1.4-py3-none-any.whl (4.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page