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

Machine learning framework for both deep learning and traditional algorithms

Explainable Medical ImageSegmentation via GenerativeAdversarial Networks andLayer-wise Relevance Propagation

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

Original code for "Zero-Shot Domain Adaptation with a Physics Prior"

基于AlphaPose的TensorRT加速

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

Reinforcement Learning with Q-Learning Algorithm on gym's frozen lake environment implemented in python

Pairwise Learning for Neural Link Prediction for OGB (PLNLP-OGB)

Artificial Neural network regression model to predict the energy output in a combined cycle power plant.

The 2nd Version Of Slothybot

DeepLearning Anomalies Detection with Bluetooth Sensor Data

This folder contains the implementation of the multi-relational attribute propagation algorithm.

Evolving neural network parameters in JAX.

Parameterized Explainer for Graph Neural Network

3ds-Ghidra-Scripts - Ghidra scripts to help with 3ds reverse engineering

Misc YOLOL scripts for use in the Starbase space sandbox videogame

Cooperative multi-agent reinforcement learning for high-dimensional nonequilibrium control

Doge-Prediction - Coding Club prediction ig

Tensorflow port of a full NetVLAD network

A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."