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

Container : Context Aggregation Network

Code and project page for ICCV 2021 paper "DisUnknown: Distilling Unknown Factors for Disentanglement Learning"

GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.

Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.

Keras udrl - Keras implementation of Upside Down Reinforcement Learning

NPBG++: Accelerating Neural Point-Based Graphics

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

Prototype python implementation of the ome-ngff table spec

Tensor-based approaches for fMRI classification

Mesh Graphormer is a new transformer-based method for human pose and mesh reconsruction from an input image

End-to-End Referring Video Object Segmentation with Multimodal Transformers

Simple-Image-Classification - Simple Image Classification Code (PyTorch)

Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021)

This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Ground truth data for the Optical Character Recognition of Historical Classical Commentaries.

Deep Learning: Architectures & Methods Project: Deep Learning for Audio Super-Resolution

Pytorch implementation of "Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech"

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).