Multi-Glimpse Network With Python

Last update: May 10, 2022

Related tags

Deep Learning MGNet

Overview

Multi-Glimpse Network

Our code requires Python ≥ 3.8

Installation

For example, venv + pip:

$ python3 -m venv env
$ source env/bin/activate
(env) $ python3 -m pip install -r requirements.txt

Evaluation

Accuracy on clean images

Create ImageNet100 from ImageNet (using symbolic links).

$ python3 tools/create_imagenet100.py tools/imagenet100.txt \
    /path/to/ImageNet /path/to/ImageNet100

Download checkpoints from Google Drive.
Test accuracy.

$ export dataset="--train_dir /path/to/ImageNet100/train \
    --val_dir /path/to/ImageNet100/val \
    --dataset imagenet --num_class 100"
# Baseline
$ python3 main.py $dataset --test --n_iter 1 --scale 1.0  --model resnet18 \
    --checkpoint resnet18_baseline
# Ours
$ python3 main.py $dataset --test --n_iter 4 --scale 2.33 --model resnet18 \
    --checkpoint resnet18_ours --alpha 0.6 --s 0.02

Add the flag --flop_count to count the approximate FLOPs for the inference of an image. (using fvcore)

Accuracy on adversarial attacks (PGD)

Test adversarial accuracy.

# Baseline
$ python3 main.py $dataset --test --n_iter 1 --scale 1.0  --adv --step_k 10 \
    --model resnet18 --checkpoint resnet18_baseline
# Ours
$ python3 main.py $dataset --test --n_iter 4 --scale 2.33 --adv --step_k 10 \
    --model resnet18 --checkpoint resnet18_ours --alpha 0.6 --s 0.02

Accuracy on common corruptions

Create ImageNet100-C from ImageNet-C (using symbolic links).

$ python3 tools/create_imagenet100c.py  \
    tools/imagenet100.txt  /path/to/ImageNet-C/ /path/to/ImageNet100-C/

Test for a single corruption.

$ export dataset="--train_dir /path/to/ImageNet100/train \
    --val_dir /path/to/ImageNet100-C/pixelate/5 \
    --dataset imagenet --num_class 100"
# Baseline
$ python3 main.py $dataset --test --n_iter 1 --scale 1.0  --model resnet18 \
    --checkpoint resnet18_baseline
# Ours
$ python3 main.py $dataset --test --n_iter 4 --scale 2.33 --model resnet18 \
    --checkpoint resnet18_ours --alpha 0.6 --s 0.02

A simple script to test all corruptions and collect results.

# Modify tools/eval_imagenet100c.py and run it to generate script
$ python3 tools/eval_imagenet100c.py /home2/ImageNet100-C/ > run.sh
# Evaluate
$ bash run.sh
# Collect results
$ python3 tools/collect_imagenet100c.py

Training

$ export dataset="--train_dir /path/to/ImageNet100/train \
    --val_dir /path/to/ImageNet100/val \
    --dataset imagenet --num_class 100"
# Baseline
$ python3 main.py $dataset --epochs 400 --n_iter 1 --scale 1.0 \
    --model resnet18 --gpu 0,1,2,3
# Ours
$ python3 main.py $dataset --epochs 400 --n_iter 4 --scale 2.33 \
    --model resnet18 --alpha 0.6 --s 0.02  --gpu 0,1,2,3

Check tensorboard for the logs. (When training with multiple gpus, the log value may be scaled by the number of gpus except for the validation accuracy)

tensorboard  --logdir=logs

Note that we left our exploration in the code for further study, e.g., self-supervised spatial guidance, dynamic gradient re-scaling operation.

Multi-Glimpse Network With Python

Related tags

Overview

Multi-Glimpse Network

Installation

Evaluation

Accuracy on clean images

Accuracy on adversarial attacks (PGD)

Accuracy on common corruptions

Training

Owner

This project is the PyTorch implementation of our CVPR 2022 paper:

Deep learning with dynamic computation graphs in TensorFlow

Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments

Real Time Object Detection and Classification using Yolo Algorithm.

Code for You Only Cut Once: Boosting Data Augmentation with a Single Cut

Tackling data scarcity in Speech Translation using zero-shot multilingual Machine Translation techniques

Behavioral "black-box" testing for recommender systems

Speech Enhancement Generative Adversarial Network Based on Asymmetric AutoEncoder

Code for paper "Learning to Reweight Examples for Robust Deep Learning"

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Cancer metastasis detection with neural conditional random field (NCRF)

This repo in the implementation of EMNLP'21 paper "SPARQLing Database Queries from Intermediate Question Decompositions" by Irina Saparina, Anton Osokin

Image Recognition using Pytorch

efficient neural audio synthesis in the waveform domain

A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.

Split Variational AutoEncoder

Implementation of CVPR'2022:Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors

PyTorch package for the discrete VAE used for DALL·E.

PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation (TPAMI).

YoloAll is a collection of yolo all versions. you you use YoloAll to test yolov3/yolov5/yolox/yolo_fastest