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.
1,539 stars. No commits in the last 6 months.
Use this if you are training DenseNets and repeatedly encounter 'out of memory' errors on your GPU, limiting the complexity or scale of your models.
Not ideal if your GPU memory is abundant and you prioritize the absolute fastest training speed over memory efficiency.
Stars
1,539
Forks
321
Language
Python
License
MIT
Category
Last pushed
Jun 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gpleiss/efficient_densenet_pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
raghakot/keras-resnet
Residual networks implementation using Keras-1.0 functional API
titu1994/DenseNet
DenseNet implementation in Keras
liuzhuang13/DenseNet
Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).
BIGBALLON/cifar-10-cnn
Play deep learning with CIFAR datasets
bamos/densenet.pytorch
A PyTorch implementation of DenseNet.