densenet.pytorch and efficient_densenet_pytorch

These two PyTorch implementations of DenseNet are competitors, as both aim to provide the core DenseNet architecture, with "gpleiss" offering specific memory efficiency advantages over "bamos".

densenet.pytorch
51
Established
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 842
Forks: 187
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 1,539
Forks: 321
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About densenet.pytorch

bamos/densenet.pytorch

A PyTorch implementation of DenseNet.

This project offers a verified implementation of the DenseNet-BC neural network architecture, built for use within the PyTorch deep learning framework. It takes image datasets like CIFAR-10 and outputs a trained image classification model with state-of-the-art performance. This is for machine learning researchers and practitioners who are building or experimenting with image recognition systems.

image-classification deep-learning computer-vision neural-networks model-training

About efficient_densenet_pytorch

gpleiss/efficient_densenet_pytorch

A memory-efficient implementation of DenseNets

This project helps deep learning engineers and researchers train DenseNet models more efficiently on GPUs. It takes your existing DenseNet architecture and reduces the GPU memory needed, making it possible to train deeper models or larger batches than before. This is ideal for those working on computer vision tasks like image classification.

deep-learning-engineering computer-vision neural-network-training image-classification

Related comparisons

Scores updated daily from GitHub, PyPI, and npm data. How scores work