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

Monocular 3D Object Detection: An Extrinsic Parameter Free Approach (CVPR2021)

Motion and Shape Capture from Sparse Markers

BoxInst: High-Performance Instance Segmentation with Box Annotations

pytorch implementation of dftd2 & dftd3

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.

Main Results on ImageNet with Pretrained Models

Pytorch implementation of Rosca, Mihaela, et al. "Variational Approaches for Auto-Encoding Generative Adversarial Networks."

WHENet - ONNX, OpenVINO, TFLite, TensorRT, EdgeTPU, CoreML, TFJS, YOLOv4/YOLOv4-tiny-3L

Implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

CVPR 2021: "Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE"

Centroid-UNet is deep neural network model to detect centroids from satellite images.

A PyTorch Implementation of Single Shot MultiBox Detector

PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers

PyTorch implementation for Convolutional Networks with Adaptive Inference Graphs

Worktory is a python library created with the single purpose of simplifying the inventory management of network automation scripts.

Pytorch Implementation of Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations

PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation.

InterfaceGAN++: Exploring the limits of InterfaceGAN

Implementation of momentum^2 teacher