All Projects → DetectionTeamUCAS → Faster Rcnn_tensorflow

DetectionTeamUCAS / Faster Rcnn_tensorflow

This is a tensorflow re-implementation of Faster R-CNN: Towards Real-Time ObjectDetection with Region Proposal Networks.

Projects that are alternatives of or similar to Faster Rcnn tensorflow

Py R Fcn Multigpu
Code for training py-faster-rcnn and py-R-FCN on multiple GPUs in caffe
Stars: ✭ 192 (+35.21%)
Mutual labels:  jupyter-notebook, faster-rcnn
Simple Faster Rcnn Pytorch
A simplified implemention of Faster R-CNN that replicate performance from origin paper
Stars: ✭ 3,422 (+2309.86%)
Mutual labels:  jupyter-notebook, faster-rcnn
Nas fpn tensorflow
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
Stars: ✭ 198 (+39.44%)
Mutual labels:  jupyter-notebook, coco
Traffic Sign Detection
Traffic Sign Detection. Code for the paper entitled "Evaluation of deep neural networks for traffic sign detection systems".
Stars: ✭ 200 (+40.85%)
Mutual labels:  jupyter-notebook, faster-rcnn
Keras Faster Rcnn
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Stars: ✭ 28 (-80.28%)
Mutual labels:  jupyter-notebook, faster-rcnn
Repo 2018
Deep Learning Summer School + Tensorflow + OpenCV cascade training + YOLO + COCO + CycleGAN + AWS EC2 Setup + AWS IoT Project + AWS SageMaker + AWS API Gateway + Raspberry Pi3 Ubuntu Core
Stars: ✭ 163 (+14.79%)
Mutual labels:  jupyter-notebook, coco
Toolbox
various cv tools, such as label tools, data augmentation, label conversion, etc.
Stars: ✭ 279 (+96.48%)
Mutual labels:  jupyter-notebook, coco
Py Rfcn Priv
code for py-R-FCN-multiGPU maintained by bupt-priv
Stars: ✭ 153 (+7.75%)
Mutual labels:  jupyter-notebook, faster-rcnn
Soft Nms
Object Detection
Stars: ✭ 708 (+398.59%)
Mutual labels:  jupyter-notebook, coco
Tf Faster Rcnn
Tensorflow Faster RCNN for Object Detection
Stars: ✭ 3,604 (+2438.03%)
Mutual labels:  faster-rcnn, coco
Pytorchnethub
项目注释+论文复现+算法竞赛
Stars: ✭ 341 (+140.14%)
Mutual labels:  jupyter-notebook, faster-rcnn
Fcos tensorflow
FCOS: Fully Convolutional One-Stage Object Detection.
Stars: ✭ 87 (-38.73%)
Mutual labels:  jupyter-notebook, coco
Bottom Up Attention
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
Stars: ✭ 989 (+596.48%)
Mutual labels:  jupyter-notebook, faster-rcnn
Robust Physical Attack
Physical adversarial attack for fooling the Faster R-CNN object detector
Stars: ✭ 115 (-19.01%)
Mutual labels:  jupyter-notebook, faster-rcnn
Machine Learning
Notes for machine learning
Stars: ✭ 142 (+0%)
Mutual labels:  jupyter-notebook
Invisible Cloak
Stars: ✭ 143 (+0.7%)
Mutual labels:  jupyter-notebook
Tensorflow Anpr
Automatic Number (License) Plate Recognition using Tensorflow Object Detection API
Stars: ✭ 142 (+0%)
Mutual labels:  faster-rcnn
Natural Language Processing Tutorials
Natural Language Processing Tutorials(NLP) with Julia and Python
Stars: ✭ 142 (+0%)
Mutual labels:  jupyter-notebook
Vmls Companions
These are companion notebooks written in Julia and Python for: "Introduction to Applied Linear Algebra" by Boyd and Vandenberghe.
Stars: ✭ 142 (+0%)
Mutual labels:  jupyter-notebook
Celeste.jl
Scalable inference for a generative model of astronomical images
Stars: ✭ 142 (+0%)
Mutual labels:  jupyter-notebook

Faster-RCNN_Tensorflow

Abstract

This is a tensorflow re-implementation of Faster R-CNN: Towards Real-Time ObjectDetection with Region Proposal Networks.

This project is completed by YangXue and YangJirui. Some relevant projects (R2CNN) and (RRPN) based on this code.

Train on VOC 2007 trainval and test on VOC 2007 test (PS. This project also support coco training.)

1

Comparison

use_voc2012_metric

Models mAP sheep horse bicycle bottle cow sofa bus dog cat person train diningtable aeroplane car pottedplant tvmonitor chair bird boat motorbike
resnet50_v1 75.16 74.08 89.27 80.27 55.74 83.38 69.35 85.13 88.80 91.42 81.17 81.71 62.74 78.65 86.86 47.00 76.71 50.29 79.05 60.51 80.96
resnet101_v1 77.03 79.68 89.33 83.89 59.41 85.68 76.59 84.23 88.50 88.50 81.54 79.16 72.66 80.26 88.42 47.50 79.81 52.85 80.70 59.94 81.87
mobilenet_v2 50.36 46.68 70.45 67.43 25.69 53.60 46.26 58.95 37.62 43.97 67.67 61.35 52.14 56.54 75.02 24.47 49.89 27.76 38.04 38.20 65.46

use_voc2007_metric

Models mAP sheep horse bicycle bottle cow sofa bus dog cat person train diningtable aeroplane car pottedplant tvmonitor chair bird boat motorbike
resnet50_v1 73.09 72.11 85.63 77.74 55.82 81.19 67.34 82.44 85.66 87.34 77.49 79.13 62.65 76.54 84.01 47.90 74.13 50.09 76.81 60.34 77.47
resnet101_v1 74.63 76.35 86.18 79.87 58.73 83.4 74.75 80.03 85.4 86.55 78.24 76.07 70.89 78.52 86.26 47.80 76.34 52.14 78.06 58.90 78.04
mobilenet_v2 50.34 46.99 68.45 65.89 28.16 53.21 46.96 57.80 38.60 44.12 66.20 60.49 52.40 56.06 72.68 26.91 49.99 30.18 39.38 38.54 64.74

Requirements

1、tensorflow >= 1.2
2、cuda8.0
3、python2.7 (anaconda2 recommend)
4、opencv(cv2)

Download Model

1、please download resnet50_v1resnet101_v1 pre-trained models on Imagenet, put it to $PATH_ROOT/data/pretrained_weights.
2、please download mobilenet_v2 pre-trained model on Imagenet, put it to $PATH_ROOT/data/pretrained_weights/mobilenet.
3、please download trained model by this project, put it to $PATH_ROOT/output/trained_weights.

Data Format

├── VOCdevkit
│   ├── VOCdevkit_train
│       ├── Annotation
│       ├── JPEGImages
│   ├── VOCdevkit_test
│       ├── Annotation
│       ├── JPEGImages

Compile

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

Demo(available)

Select a configuration file in the folder ($PATH_ROOT/libs/configs/) and copy its contents into cfgs.py, then download the corresponding weights.

cd $PATH_ROOT/tools
python inference.py --data_dir='/PATH/TO/IMAGES/' 
                    --save_dir='/PATH/TO/SAVE/RESULTS/' 
                    --GPU='0'

Eval

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

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 line 76 of $PATH_ROOT/data/io/read_tfrecord.py 

2、make tfrecord

cd $PATH_ROOT/data/io/  
python convert_data_to_tfrecord.py --VOC_dir='/PATH/TO/VOCdevkit/VOCdevkit_train/' 
                                   --xml_dir='Annotation'
                                   --image_dir='JPEGImages'
                                   --save_name='train' 
                                   --img_format='.jpg' 
                                   --dataset='pascal'

3、train

cd $PATH_ROOT/tools
python train.py

Tensorboard

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

2 1

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

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].