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

[CVPR 2021 Oral] Variational Relational Point Completion Network

Official repository for MixFaceNets: Extremely Efficient Face Recognition Networks

SegNet-like Autoencoders in TensorFlow

UT-Sarulab MOS prediction system using SSL models

Pre-trained NFNets with 99% of the accuracy of the official paper

An algorithm that handles large-scale aerial photo co-registration, based on SURF, RANSAC and PyTorch autograd.

Adaptive Attention Span for Reinforcement Learning

Implementation of ICCV21 paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers

For visualizing the dair-v2x-i dataset

Company clustering with K-means/GMM and visualization with PCA, t-SNE, using SSAN relation extraction

This is the code of "Multi-view Contrastive Graph Clustering" in NeurlPS 2021.

ARAE-Tensorflow for Discrete Sequences (Adversarially Regularized Autoencoder)

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

Light-Head R-CNN

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks

Full Resolution Residual Networks for Semantic Image Segmentation

DeepLab-ResNet rebuilt in TensorFlow

Deep-learning X-Ray Micro-CT image enhancement, pore-network modelling and continuum modelling

reimpliment of DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

Classification models 1D Zoo - Keras and TF.Keras