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

Source code of our TTH paper: Targeted Trojan-Horse Attacks on Language-based Image Retrieval.

FastCover: A Self-Supervised Learning Framework for Multi-Hop Influence Maximization in Social Networks by Anonymous.

Dense Prediction Transformers

PyTorch implementation of "A Simple Baseline for Low-Budget Active Learning".

CS583: Deep Learning

Vehicles Counting using YOLOv4 + DeepSORT + Flask + Ngrok

Implementation of Lie Transformer, Equivariant Self-Attention, in Pytorch

PyTorch implementaton of our CVPR 2021 paper "Bridging the Visual Gap: Wide-Range Image Blending"

SMIS - Semantically Multi-modal Image Synthesis(CVPR 2020)

Repo for "Event-Stream Representation for Human Gaits Identification Using Deep Neural Networks"

[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning

Dense Gaussian Processes for Few-Shot Segmentation

Only works with the dashboard version / branch of jesse

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

Anonymous implementation of KSL

Official Implementation of 'UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers' ICLR 2021(spotlight)

A Self-Supervised Contrastive Learning Framework for Aspect Detection

Vignette is a face tracking software for characters using osu!framework.

Used to record WKU's utility bills on a regular basis.

A set of tools to pre-calibrate and calibrate (multi-focus) plenoptic cameras (e.g., a Raytrix R12) based on the libpleno.