GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → DetectionTeamUCAS → Fcos_tensorflow

DetectionTeamUCAS / Fcos_tensorflow

Licence: mit
FCOS: Fully Convolutional One-Stage Object Detection.

Labels

jupyter-notebooktensorflowobject-detectioncoco

Projects that are alternatives of or similar to Fcos tensorflow

Nas fpn tensorflow
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
Stars: ✭ 198 (+127.59%)
Mutual labels:  object-detection, jupyter-notebook, coco
Simple Ssd For Beginners
This repository contains easy SSD(Single Shot MultiBox Detector) implemented with Pytorch and is easy to read and learn
Stars: ✭ 33 (-62.07%)
Mutual labels:  object-detection, jupyter-notebook
Keras Faster Rcnn
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Stars: ✭ 28 (-67.82%)
Mutual labels:  object-detection, jupyter-notebook
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+9341.38%)
Mutual labels:  object-detection, jupyter-notebook
Soft Nms
Object Detection
Stars: ✭ 708 (+713.79%)
Mutual labels:  jupyter-notebook, coco
Getting Things Done With Pytorch
Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BERT.
Stars: ✭ 738 (+748.28%)
Mutual labels:  object-detection, jupyter-notebook
Tensorflow Serving sidecar
Serve machine learning models using tensorflow serving
Stars: ✭ 41 (-52.87%)
Mutual labels:  object-detection, coco
Detectorch
Detectorch - detectron for PyTorch
Stars: ✭ 566 (+550.57%)
Mutual labels:  object-detection, jupyter-notebook
Math object detection
An image recognition/object detection model that detects handwritten digits and simple math operators. The output of the predicted objects (numbers & math operators) is then evaluated and solved.
Stars: ✭ 52 (-40.23%)
Mutual labels:  object-detection, coco
Mish
Official Repsoitory for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Stars: ✭ 1,072 (+1132.18%)
Mutual labels:  object-detection, jupyter-notebook
Mmdetection object detection demo
How to train an object detection model with mmdetection
Stars: ✭ 55 (-36.78%)
Mutual labels:  object-detection, jupyter-notebook
Saliency
TensorFlow implementation for SmoothGrad, Grad-CAM, Guided backprop, Integrated Gradients and other saliency techniques
Stars: ✭ 648 (+644.83%)
Mutual labels:  object-detection, jupyter-notebook
Deep Learning For Hackers
Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)
Stars: ✭ 586 (+573.56%)
Mutual labels:  object-detection, jupyter-notebook
Dataaugmentationforobjectdetection
Data Augmentation For Object Detection
Stars: ✭ 812 (+833.33%)
Mutual labels:  object-detection, jupyter-notebook
Centernet2
Two-stage CenterNet
Stars: ✭ 496 (+470.11%)
Mutual labels:  object-detection, coco
Image bbox slicer
This easy-to-use library splits images and its bounding box annotations into tiles, both into specific sizes and into any arbitrary number of equal parts. It can also resize them, both by specific sizes and by a resizing/scaling factor.
Stars: ✭ 41 (-52.87%)
Mutual labels:  object-detection, jupyter-notebook
Fish detection
Fish detection using Open Images Dataset and Tensorflow Object Detection
Stars: ✭ 67 (-22.99%)
Mutual labels:  object-detection, jupyter-notebook
Yet Another Efficientdet Pytorch
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
Stars: ✭ 4,945 (+5583.91%)
Mutual labels:  object-detection, jupyter-notebook
Curve Text Detector
This repository provides train＆test code, dataset, det.&rec. annotation, evaluation script, annotation tool, and ranking.
Stars: ✭ 551 (+533.33%)
Mutual labels:  object-detection, jupyter-notebook
Tensorflow Lite Rest Server
Expose tensorflow-lite models via a rest API
Stars: ✭ 43 (-50.57%)
Mutual labels:  object-detection, jupyter-notebook
View All Similar Projects ➔

FCOS: Fully Convolutional One-Stage Object Detection

Abstract

This is a tensorflow re-implementation of FCOS: Fully Convolutional One-Stage Object Detection, and completed by YangXue.

Performance

Model Backbone Training data Val data mAP Inf time (fps) Model Link Train Schedule GPU Image/GPU Configuration File
Faster-RCNN ResNet50_v1 600 VOC07 trainval VOC07 test 73.09 - - - 1X GTX 1080Ti 1 -
FPN ResNet50_v1 600 VOC07 trainval VOC07 test 74.26 - - - 1X GTX 1080Ti 1 -
RetinaNet ResNet50_v1d 600 VOC07 trainval VOC07 test 74.00 14.6 model - 4X GeForce RTX 2080 Ti 2 -
FCOS ResNet50_v1d 896 VOC07 trainval VOC07 test 72.25 14.3 Baidu Drive (ujvj) - 3X GeForce RTX 2080 Ti 2 cfgs_fcos_voc07_res50_v4.py
RetinaNet ResNet50_v1d 600 COCO train2017 COCO val2017 (coco minival) 34.3 (paper: 34.0) 12.2 model 1x 4X GeForce RTX 2080 Ti 2 -
FCOS ResNet50_v1d 600 COCO train2017 COCO val2017 (coco minival) 34.8 12.2 Baidu Drive (qg62) 1x 3X GeForce RTX 2080 Ti 2 cfgs_fcos_coco_res50_1x_v1.py

My Development Environment

1、python3.5 (anaconda recommend)
2、cuda10.0
3、opencv(cv2)
4、tfplot (optional)
5、tensorflow >= 1.12

Download Model

Pretrain weights

1、Please download resnet50_v1, resnet101_v1 pre-trained models on Imagenet, put it to data/pretrained_weights.
2、(Recommend in this repo) Or you can choose to use a better backbone, refer to gluon2TF.

Others

1、COCO dataset related

Compile

cd $PATH_ROOT/libs/box_utils/cython_utils
python setup.py build_ext --inplace

cd $PATH_ROOT/libs/box_utils/nms
python setup.py build_ext --inplace

Train

1、If you want to train your own data, please note:

(1) Modify parameters (such as CLASS_NUM, DATASET_NAME, VERSION, etc.) in $PATH_ROOT/libs/configs/cfgs.py
(2) Add category information in $PATH_ROOT/libs/label_name_dict/lable_dict.py     
(3) Add data_name to $PATH_ROOT/data/io/read_tfrecord.py

2、Make tfrecord

cd $PATH_ROOT/data/io/  
python convert_data_to_tfrecord_coco.py --VOC_dir='/PATH/TO/JSON/FILE/' 
                                        --save_name='train' 
                                        --dataset='coco'

3、Multi-gpu train

cd $PATH_ROOT/tools
multi_gpu_train.py

Eval

COCO

cd $PATH_ROOT/tools
python eval_coco.py --eval_data='/PATH/TO/IMAGES/'  
                    --eval_gt='/PATH/TO/TEST/ANNOTATION/'
                    --gpus='0,1,2,3,4,5,6,7'

PASCAL VOC

cd $PATH_ROOT/tools
python eval.py --eval_dir='/PATH/TO/IMAGES/'  
               --annotation_dir='/PATH/TO/TEST/ANNOTATION/'
               --gpu='0'

Tensorboard

cd $PATH_ROOT/output/summary
tensorboard --logdir=.

3

4

Reference

1、https://github.com/endernewton/tf-faster-rcnn
2、https://github.com/zengarden/light_head_rcnn
3、https://github.com/tensorflow/models/tree/master/research/object_detection
4、https://github.com/CharlesShang/FastMaskRCNN
5、https://github.com/matterport/Mask_RCNN
6、https://github.com/msracver/Deformable-ConvNets
7、https://github.com/tianzhi0549/FCOS

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].