packnet

Task Network Pruning Framework

A deep learning framework for adding multiple tasks to a single network by iterative pruning and evaluation on various datasets.

Code for PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

GitHub

230 stars
7 watching
40 forks
Language: Python
last commit: almost 8 years ago

Related projects:

RepositoryDescriptionStars
arunmallya/piggybackAdapting a single network to multiple tasks by learning to mask weights183
ntumslab/pruneA framework for unsupervised network embedding using a multi-task Siamese neural network45
alecwangcq/eigendamage-pytorchA deep learning project implementing structured pruning algorithms in PyTorch for efficient neural network training and inference.112
neuralmagic/sparsemlEnables the creation of smaller neural network models through efficient pruning and quantization techniques2,083
prinsphield/adversarial_reprogrammingThis project enables reprogramming of pre-trained neural networks to work on new tasks by fine-tuning them on smaller datasets.33
rocm/mxnetA deep learning framework that enables efficient and flexible distributed/mobile deep learning with dynamic dataflow dependency scheduling28
taolei87/rcnnAn implementation of neural network components and optimization methods for text analysis, including rationales for neural predictions.355
hyeonwoonoh/decouplednetA deep learning framework for semantic segmentation using pre-trained classification networks and heterogeneous annotations74
tusimple/sparse-structure-selectionRe-implements sparse structure selection algorithm for deep neural networks in a modified MXNet framework.87
jacobgil/pytorch-pruningThis project provides a PyTorch implementation of pruning techniques to reduce the computational resources required for neural network inference.877
microsoft/archaiAutomates the search for optimal neural network configurations in deep learning applications468
mrkn/mxnet.rbA Ruby interface to MXNet's deep learning framework48
taehoonlee/tensornetsA collection of pre-trained neural network models with simple interfaces for easy integration into machine learning workflows.1,004
fedml-ai/spreadgnnA framework for decentralized multi-task learning of graph neural networks on molecular data with guaranteed convergence44
bayeswatch/pytorch-prunesA tool for training neural networks with pruned weights and evaluating their performance.140