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