Official pytorch code for "APP: Anytime Progressive Pruning"

Last update: Nov 22, 2022

Overview

APP: Anytime Progressive Pruning

Diganta Misra^1,2,3, Bharat Runwal^2,4, Tianlong Chen⁵, Zhangyang Wang⁵, Irina Rish^1,3

¹ Mila - Quebec AI Institute,² Landskape AI,³ UdeM,⁴ IIT-Delhi,⁵ VITA, UT-Austin

Requirements

To create a new conda environment with the dependencies used in this project, do:

conda env create -f app.yml

For running the code on Restricted-Imagenet Dataset, first install the robustness library from here and provide the imagenet_path argument as the path to the imaganet data folder.

Run the Code

Here is an example of running the Anytime Progressive Pruning (APP) on Cifar-10 dataset with 8 megabatches in total:

python main_anytime_train.py \
    --data ../data \
    --dataset cifar10 \
    --arch resnet50 \
    --seed 1 \
    --epochs 50 \
    --decreasing_lr 20,40 \
    --batch_size 64 \
    --weight_decay 1e-4 \
    --meta_batch_size 6250 \
    --meta_batch_number 8 \
    --sparsity_level 4.5 \
    --snip_size 0.20 \
    --save_dir c10_r50

One-Shot pruning :

python main_anytime_one.py \
    --data ../data \
    --dataset cifar10 \
    --arch resnet50 \
    --seed 1 \
    --epochs 50 \
    --decreasing_lr 20,40 \
    --batch_size 64 \
    --weight_decay 1e-4 \
    --meta_batch_size 6250 \
    --meta_batch_number 8 \
    --sparsity_level 4.5 \
    --snip_size 0.20 \
    --save_dir c10_OSP_r18

Baseline :

python main_anytime_baseline.py \
    --data ../data \
    --dataset cifar10 \
    --arch resnet50 \
    --seed 1 \
    --epochs 50 \
    --decreasing_lr 20,40 \
    --batch_size 64 \
    --weight_decay 1e-4 \
    --meta_batch_size 6250 \
    --meta_batch_number 8 \
    --save_dir c10_BASE_r50

Cite:

@misc{misra2022app,
    title={APP: Anytime Progressive Pruning},
    author={Diganta Misra and Bharat Runwal and Tianlong Chen and Zhangyang Wang and Irina Rish},
    year={2022},
    eprint={2204.01640},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

Official pytorch code for "APP: Anytime Progressive Pruning"

Related tags

Overview

APP: Anytime Progressive Pruning

Requirements

Run the Code

Cite:

Owner

Landskape AI

VQMIVC - Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion

Using image super resolution models with vapoursynth and speeding them up with TensorRT

Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021

Implementing yolov4 target detection and tracking based on nao robot

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks.

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

Learning to See by Looking at Noise

Implementation of a Transformer using ReLA (Rectified Linear Attention)

Build fully-functioning computer vision models with PyTorch

Blender add-on: Add to Cameras menu: View → Camera, View → Add Camera, Camera → View, Previous Camera, Next Camera

Points2Surf: Learning Implicit Surfaces from Point Clouds (ECCV 2020 Spotlight)

Affine / perspective transformation in Pose Estimation with Tensorflow 2

library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

Source code, datasets and trained models for the paper Learning Advanced Mathematical Computations from Examples (ICLR 2021), by François Charton, Amaury Hayat (ENPC-Rutgers) and Guillaume Lample

Level Based Customer Segmentation

A lightweight face-recognition toolbox and pipeline based on tensorflow-lite

LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models

MANO hand model porting for the GraspIt simulator

Equivariant Imaging: Learning Beyond the Range Space

Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021.