ObjectDetNet is an easy, flexible, open-source object detection framework

Overview

Getting started with the ObjectDetNet

ObjectDetNet is an easy, flexible, open-source object detection framework which allows you to easily train, resume & prototype training sessions, run inference and flexibly work with checkpoints in a production grade environment.

Quick Start

Copy and paste this into your command line

#run in docker 
docker run --rm -it --init  --runtime=nvidia  --ipc=host  -e NVIDIA_VISIBLE_DEVICES=0 buffalonoam/zazu-image:0.3 bash

mkdir data
cd data
git clone https://github.com/dataloop-ai/tiny_coco.git
cd ..
git clone https://github.com/dataloop-ai/ObjectDetNet.git
cd ObjectDetNet
python main.py --train

After training just run:

python main.py --predict 
# OR 
python main.py --predict_single
# to predict a single item

To change the data you run on or the parameters of your model just update the example_checkpoint.pt file!

At the core of the ObjectDetNet framework is the checkpoint object. The checkpoint object is a json, pt or json styled file to be loaded into python as a dictionary. Checkpoint objects aren't just used for training, but also necessary for running inference. Bellow is an example of how a checkpoint object might look.

├── {} devices
│   ├── {} gpu_index
│       ├── 0
├── {} model_specs
│   ├── {} name
│       ├── retinanet
│   ├── {} training_configs
│       ├── {} depth
│           ├── 152
│       ├── {} input_size
│       ├── {} learning_rate
│   ├── {} data
│       ├── {} home_path
│       ├── {} annotation_type
│           ├── coco
│       ├── {} dataset_name
├── {} hp_values
│       ├── {} learning_rate
│       ├── {} tuner/epochs
│       ├── {} tuner/initial_epoch
├── {} labels
│       ├── {} 0
│           ├── Rodent
│       ├── {} 1
│       ├── {} 2
├── {} metrics
│       ├── {} val_accuracy
│           ├── 0.834
├── {} model
├── {} optimizer
├── {} scheduler
├── {} epoch
│       ├── 18

For training your checkpoint dictionary must have the following keys:

  • device - gpu index for which to convert all tensors
  • model_specs - contains 3 fields
    1. name
    2. training_configs
    3. data

To resume training you'll also need:

  • model - contains state of model weights
  • optimizer - contains state of optimizer
  • scheduler - contains state of scheduler
  • epoch - to know what epoch to start from

To run inference your checkpoint will need:

  • model_specs
  • labels

If you'd like to customize by adding your own model, check out Adding a Model

Feel free to reach out with any questions

WeChat: BuffaloNoam
Line: buffalonoam
WhatsApp: +972524226459

Refrences

Thank you to these repositories for their contributions to the ObjectDetNet

Repository features UNet inspired architecture used for segmenting lungs on chest X-Ray images

Lung Segmentation (2D) Repository features UNet inspired architecture used for segmenting lungs on chest X-Ray images. Demo See the application of the

163 Sep 21, 2022
The code repository for "PyCIL: A Python Toolbox for Class-Incremental Learning" in PyTorch.

PyCIL: A Python Toolbox for Class-Incremental Learning Introduction • Methods Reproduced • Reproduced Results • How To Use • License • Acknowledgement

Fu-Yun Wang 258 Dec 31, 2022
The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing".

BMC The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing". BibTex entry available here. B

Orange 383 Dec 16, 2022
Dense matching library based on PyTorch

Dense Matching A general dense matching library based on PyTorch. For any questions, issues or recommendations, please contact Prune at

Prune Truong 399 Dec 28, 2022
social humanoid robots with GPGPU and IoT

Social humanoid robots with GPGPU and IoT Social humanoid robots with GPGPU and IoT Paper Authors Mohsen Jafarzadeh, Stephen Brooks, Shimeng Yu, Balak

0 Jan 07, 2022
Implementation for the paper 'YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs'

YOLO-ReT This is the original implementation of the paper: YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs. Prakhar Ganesh, Ya

69 Oct 19, 2022
An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities.

Playground for CLIP-like models Demo Colab Link GradCAM Visualization Naive Zero-shot Detection Smarter Zero-shot Detection Captcha Solver Changelog 2

Kevin Zakka 101 Dec 30, 2022
This is the replication package for paper submission: Towards Training Reproducible Deep Learning Models.

This is the replication package for paper submission: Towards Training Reproducible Deep Learning Models.

0 Feb 02, 2022
🍷 Gracefully claim weekly free games and monthly content from Epic Store.

EPIC 免费人 🚀 优雅地领取 Epic 免费游戏 Introduction 👋 Epic AwesomeGamer 帮助玩家优雅地领取 Epic 免费游戏。 使用 「Epic免费人」可以实现如下需求: get:搬空游戏商店,获取所有常驻免费游戏与免费附加内容; claim:领取周免游戏及其免

571 Dec 28, 2022
Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(2021) paper

Semantic Diversity Learning for Zero-Shot Multi-label Classification Paper Official PyTorch Implementation Avi Ben-Cohen, Nadav Zamir, Emanuel Ben Bar

28 Aug 29, 2022
Framework to build and train RL algorithms

RayLink RayLink is a RL framework used to build and train RL algorithms. RayLink was used to build a RL framework, and tested in a large-scale multi-a

Bytedance Inc. 32 Oct 07, 2022
Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

Learning View Priors for Single-view 3D Reconstruction (CVPR 2019) This is code for a paper Learning View Priors for Single-view 3D Reconstruction by

Hiroharu Kato 38 Aug 17, 2022
[NeurIPS-2021] Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation

Efficient Graph Similarity Computation - (EGSC) This repo contains the source code and dataset for our paper: Slow Learning and Fast Inference: Effici

24 Dec 31, 2022
text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.

text recognition toolbox 1. 项目介绍 该项目是基于pytorch深度学习框架,以统一的改写方式实现了以下6篇经典的文字识别论文,论文的详情如下。该项目会持续进行更新,欢迎大家提出问题以及对代码进行贡献。 模型 论文标题 发表年份 模型方法划分 CRNN 《An End-t

168 Dec 24, 2022
PyTorch implementation for "HyperSPNs: Compact and Expressive Probabilistic Circuits", NeurIPS 2021

HyperSPN This repository contains code for the paper: HyperSPNs: Compact and Expressive Probabilistic Circuits "HyperSPNs: Compact and Expressive Prob

8 Nov 08, 2022
Open-World Entity Segmentation

Open-World Entity Segmentation Project Website Lu Qi*, Jason Kuen*, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia This projec

DV Lab 410 Jan 03, 2023
A sequence of Jupyter notebooks featuring the 12 Steps to Navier-Stokes

CFD Python Please cite as: Barba, Lorena A., and Forsyth, Gilbert F. (2018). CFD Python: the 12 steps to Navier-Stokes equations. Journal of Open Sour

Barba group 2.6k Dec 30, 2022
The InterScript dataset contains interactive user feedback on scripts generated by a T5-XXL model.

Interscript The Interscript dataset contains interactive user feedback on a T5-11B model generated scripts. Dataset data.json contains the data in an

AI2 8 Dec 01, 2022
Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

GINC small-scale in-context learning dataset GINC (Generative In-Context learning Dataset) is a small-scale synthetic dataset for studying in-context

P-Lambda 29 Dec 19, 2022
Anderson Acceleration for Deep Learning

Anderson Accelerated Deep Learning (AADL) AADL is a Python package that implements the Anderson acceleration to speed-up the training of deep learning

Oak Ridge National Laboratory 7 Nov 24, 2022