An implementation of RetinaNet in PyTorch.

Last update: Jan 04, 2023

Overview

RetinaNet

An implementation of RetinaNet in PyTorch.

Installation
Training
Evaluation
Todo
Credits

Installation

Install PyTorch and torchvision.
For faster data augmentation, install pillow-simd:

pip uninstall -y pillow
pip install pillow-simd

Training

COCO 2017

First, install pycocotools:

git clone https://github.com/pdollar/coco/
cd coco/PythonAPI
make
python setup.py install
cd ../..
rm -r coco

Then download COCO 2017 into ./datasets/COCO/:

cd datasets
mkdir COCO
cd COCO

If your using wget:

wget http://images.cocodataset.org/zips/train2017.zip &&
wget http://images.cocodataset.org/zips/val2017.zip &&
wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip

If your using aria2c (recommended on for higher bandwidth connections and for allowing resumption of the download. Tune the number of max concurrent downloads (-j) and max connections per server (-x) as needed:

aria2c -x 10 -j 10 http://images.cocodataset.org/zips/train2017.zip &&
aria2c -x 10 -j 10 http://images.cocodataset.org/zips/val2017.zip &&
aria2c -x 10 -j 10 http://images.cocodataset.org/annotations/annotations_trainval2017.zip

unzip *.zip
rm *.zip

Then just run:

python train_coco.py

Pascal VOC

cd datasets
mkdir VOC
cd VOC

wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar &&
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar &&
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar

aria2c -x 10 -j 10 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar &&
aria2c -x 10 -j 10 http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar &&
aria2c -x 10 -j 10 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar

tar xf *.tar
rm *.tar

Then just run:

python train_voc.py

Custom Dataset

Lots to write here. 😉

Evaluation

To evaluate an image on a trained model:

python eval.py [checkpoint_path] [image_path]

This will create an image (output.jpg) with bounding box annotations.

Todo

Finish converting the COCO dataset class to work with batches.
Train COCO 2017 for 90,000 iterations and save a reusable checkpoint.
Try training on Pascal VOC and add download instructions.
Produce bounding box outputs for a few sanity check images.
Upload trained weights to Github releases.
Train on the 🔮 magic proprietary dataset ✨ .

An implementation of RetinaNet in PyTorch.

Related tags

Overview

RetinaNet

Installation

Training

COCO 2017

Pascal VOC

Custom Dataset

Evaluation

Todo

Credits

Owner

Conner Vercellino

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).

Convolutional neural network that analyzes self-generated images in a variety of languages to find etymological similarities

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

A python program to hack instagram

An alarm clock coded in Python 3 with Tkinter

Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing

Auto HMM: Automatic Discrete and Continous HMM including Model selection

Recursive Bayesian Networks

Malmo Collaborative AI Challenge - Team Pig Catcher

PyImpetus is a Markov Blanket based feature subset selection algorithm that considers features both separately and together as a group in order to provide not just the best set of features but also the best combination of features

Official implementation for paper Render In-between: Motion Guided Video Synthesis for Action Interpolation

render sprites into your desktop environment as shaped windows using GTK

No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

This project deploys a yolo fastest model in the form of tflite on raspberry 3b+. The model is from another repository of mine called -Trash-Classification-Car

A collection of metrics for evaluating timbre dissimilarity using the TorchMetrics API

Keras-retinanet - Keras implementation of RetinaNet object detection.

Deep Learning Based Fasion Recommendation System for Ecommerce

Process text, including tokenizing and representing sentences as vectors and Applying some concepts like RNN, LSTM and GRU to create a classifier can detect the language in which a sentence is written from among 17 languages.