All Projects → DetectionTeamUCAS → RetinaNet_Tensorflow

DetectionTeamUCAS / RetinaNet_Tensorflow

Licence: MIT License
Focal Loss for Dense Object Detection.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to RetinaNet Tensorflow

Efficientdet.pytorch
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
Stars: ✭ 1,383 (+2559.62%)
Mutual labels:  coco, pascal-voc
Soft Nms
Object Detection
Stars: ✭ 708 (+1261.54%)
Mutual labels:  coco, pascal-voc
Imglab
To speedup and simplify image labeling/ annotation process with multiple supported formats.
Stars: ✭ 723 (+1290.38%)
Mutual labels:  coco, pascal-voc
datumaro
Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.
Stars: ✭ 274 (+426.92%)
Mutual labels:  coco, pascal-voc
DetectionMetrics
Tool to evaluate deep-learning detection and segmentation models, and to create datasets
Stars: ✭ 66 (+26.92%)
Mutual labels:  coco, pascal-voc
DA-RetinaNet
Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
Stars: ✭ 31 (-40.38%)
Mutual labels:  pascal-voc, retinanet
PyTorch-Spiking-YOLOv3
A PyTorch implementation of Spiking-YOLOv3. Two branches are provided, based on two common PyTorch implementation of YOLOv3(ultralytics/yolov3 & eriklindernoren/PyTorch-YOLOv3), with support for Spiking-YOLOv3-Tiny at present.
Stars: ✭ 144 (+176.92%)
Mutual labels:  coco, pascal-voc
simpleAICV-pytorch-ImageNet-COCO-training
SimpleAICV:pytorch training example on ImageNet(ILSVRC2012)/COCO2017/VOC2007+2012 datasets.Include ResNet/DarkNet/RetinaNet/FCOS/CenterNet/TTFNet/YOLOv3/YOLOv4/YOLOv5/YOLOX.
Stars: ✭ 276 (+430.77%)
Mutual labels:  coco, retinanet
CoCoC
C development system for (Nitr)OS9/6x09, with source
Stars: ✭ 22 (-57.69%)
Mutual labels:  coco
RePRI-for-Few-Shot-Segmentation
(CVPR 2021) Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166
Stars: ✭ 130 (+150%)
Mutual labels:  coco
SegCaps
A Clone version from Original SegCaps source code with enhancements on MS COCO dataset.
Stars: ✭ 62 (+19.23%)
Mutual labels:  coco
smd
Simple mmdetection CPU inference
Stars: ✭ 27 (-48.08%)
Mutual labels:  retinanet
pdq evaluation
Evaluation code for using probabilistic detection quality (PDQ) measure for probabilistic object detection tasks. Currently supports COCO and robotic vision challenge (RVC) data.
Stars: ✭ 34 (-34.62%)
Mutual labels:  coco
OneTwoStep
CC游戏案例之 激流竞速
Stars: ✭ 17 (-67.31%)
Mutual labels:  coco
Cascade FPN Tensorflow
Cascade R-CNN: Delving into High Quality Object Detection.
Stars: ✭ 36 (-30.77%)
Mutual labels:  coco
Object-Detection-Tensorflow
Object Detection API Tensorflow
Stars: ✭ 275 (+428.85%)
Mutual labels:  retinanet
pascal voc tools
some tools about pascal voc format dataset
Stars: ✭ 24 (-53.85%)
Mutual labels:  pascal-voc
wider-face-pascal-voc-annotations
WIDER FACE annotations converted to the Pascal VOC XML format
Stars: ✭ 71 (+36.54%)
Mutual labels:  pascal-voc
RetinaNet-tensorflow
RetinaNet in tensorflow
Stars: ✭ 27 (-48.08%)
Mutual labels:  retinanet
JSON2YOLO
Convert JSON annotations into YOLO format.
Stars: ✭ 222 (+326.92%)
Mutual labels:  coco

Focal Loss for Dense Object Detection

Abstract

This is a tensorflow re-implementation of Focal Loss for Dense Object Detection, and it is completed by YangXue.

1

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_v1 600 VOC07 trainval VOC07 test 73.16 - - - 8X GeForce RTX 2080 Ti 1 cfgs_res50_voc07_v3.py
RetinaNet ResNet50_v1d 600 VOC07 trainval VOC07 test 73.26 - - - 8X GeForce RTX 2080 Ti 1 cfgs_res50_voc07_v4.py
RetinaNet ResNet50_v1d 600 VOC07 trainval VOC07 test 74.00 14.6 model - 4X GeForce RTX 2080 Ti 2 cfgs_res50_voc07_v5.py
RetinaNet ResNet50_v1d 600 VOC07+12 trainval VOC07 test 79.66 - - - 8X GeForce RTX 2080 Ti 1 cfgs_res50_voc0712_v1.py
RetinaNet ResNet101_v1d 600 VOC07+12 trainval VOC07 test 81.69 - - - 8X GeForce RTX 2080 Ti 1 cfgs_res50_voc0712_v4.py
RetinaNet ResNet101_v1d 800 VOC07+12 trainval VOC07 test 80.69 - - - 8X GeForce RTX 2080 Ti 1 cfgs_res50_voc0712_v3.py
RetinaNet ResNet50_v1d 600 COCO train2017 COCO val2017 (coco minival) 33.4 12.2 - 1x 8X GeForce RTX 2080 Ti 1 cfgs_res50_coco_1x_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 cfgs_res50_coco_1x_v5.py

My Development Environment

1、python3.5 (anaconda recommend)
2、cuda9.0
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

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_batch.py

Eval

COCO

cd $PATH_ROOT/tools
python eval_coco.py --eval_data='/PATH/TO/IMAGES/'  
                    --eval_gt='/PATH/TO/TEST/ANNOTATION/'
                    --gpu='0'
                    
cd $PATH_ROOT/tools
python eval_coco_multiprocessing.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/fizyr/keras-retinanet

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].