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

Few-shot Learning of GPT-3

Pytorch implementation of the paper: "SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Image Deraining"

Server files for UltimateLabeling

The King is Naked: on the Notion of Robustness for Natural Language Processing

Pytorch implementation for the Temporal and Object Quantification Networks (TOQ-Nets).

FAST-RIR: FAST NEURAL DIFFUSE ROOM IMPULSE RESPONSE GENERATOR

JDet is Object Detection Framework based on Jittor.

Crosslingual Segmental Language Model

Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features

Hierarchical Cross-modal Talking Face Generation with Dynamic Pixel-wise Loss （ATVGnet）

Embodied Intelligence via Learning and Evolution

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection

[CVPR 2022] Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement

Face Library is an open source package for accurate and real-time face detection and recognition

Patch Rotation: A Self-Supervised Auxiliary Task for Robustness and Accuracy of Supervised Models

YOLOX-RMPOLY

This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

Flappy bird automation using Neuroevolution of Augmenting Topologies (NEAT) in Python

Adjusting for Autocorrelated Errors in Neural Networks for Time Series

A PyTorch implementation of DenseNet.