StijnVerdenius / SNIP-it
This repository is the official implementation of the paper Pruning via Iterative Ranking of Sensitivity Statistics and implements novel pruning / compression algorithms for deep learning / neural networks. Amongst others it implements structured pruning before training, its actual parameter shrinking and unstructured before/during training.
☆31Updated last year
Related projects ⓘ
Alternatives and complementary repositories for SNIP-it
- Lookahead: A Far-sighted Alternative of Magnitude-based Pruning (ICLR 2020)☆33Updated 4 years ago
- Soft Threshold Weight Reparameterization for Learnable Sparsity☆87Updated last year
- ☆14Updated 3 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆101Updated 4 years ago
- SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY☆111Updated 5 years ago
- Neuron Merging: Compensating for Pruned Neurons (NeurIPS 2020)☆41Updated 3 years ago
- Differentiable Data Augmentation Library☆120Updated 2 years ago
- [NeurIPS'20] GradAug: A New Regularization Method for Deep Neural Networks☆93Updated 3 years ago
- Code for Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot☆43Updated 4 years ago
- Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights☆182Updated 5 years ago
- Code for paper "Orthogonal Convolutional Neural Networks".☆113Updated 3 years ago
- Code for the paper "Training Binary Neural Networks with Bayesian Learning Rule☆37Updated 2 years ago
- Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients☆29Updated 2 years ago
- ☆220Updated 3 months ago
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.☆54Updated 3 years ago
- Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.☆105Updated 5 years ago
- ☆70Updated 4 years ago
- PyTorch implementation of shake-drop regularization☆54Updated 4 years ago
- A research library for pytorch-based neural network pruning, compression, and more.☆160Updated last year
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆46Updated 3 years ago
- Evaluating AlexNet features at various depths☆39Updated 4 years ago
- Code for "Supermasks in Superposition"☆117Updated last year
- A Re-implementation of Fixed-update Initialization☆151Updated 5 years ago
- Code for our ICML'2020 paper "Stabilizing Differentiable Architecture Search via Perturbation-based Regularization"☆76Updated 3 years ago
- [NeurIPS '18] "Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?" Official Implementation.☆127Updated 2 years ago
- DropNet: Reducing Neural Network Complexity via Iterative Pruning (ICML 2020)☆15Updated 4 years ago
- pytorch-tiny-imagenet☆166Updated 11 months ago
- ContinualAI Wiki: a collaborative wiki on Continual/Lifelong Machine Learning☆49Updated 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆60Updated 3 years ago
- A repository to keep track of literature on catastrophic forgetting☆36Updated 4 years ago