https://github.com/Stick-To/Object-Detection-Tensorflow

Object Detection API Tensorflow
https://github.com/Stick-To/Object-Detection-Tensorflow

centernet detection-api-tensorflow fcos image-augmentor lightheadrcnn object-detection pfpnet rcnn refinedet retinanet ssd tensorflow yolo

Last synced: 12 days ago
JSON representation

Object Detection API Tensorflow

• Host: GitHub
• URL: https://github.com/Stick-To/Object-Detection-Tensorflow
• Owner: Stick-To
• License: mit
• Created: 2019-05-16T13:02:45.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2021-05-02T08:22:25.000Z (about 3 years ago)
• Last Synced: 2024-02-29T07:35:07.048Z (4 months ago)
• Topics: centernet, detection-api-tensorflow, fcos, image-augmentor, lightheadrcnn, object-detection, pfpnet, rcnn, refinedet, retinanet, ssd, tensorflow, yolo
• Language: Python
• Homepage:
• Size: 228 KB
• Stars: 272
• Watchers: 15
• Forks: 93
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-yolo-object-detection - Stick-To/Object-Detection-Tensorflow - To/Object-Detection-Tensorflow?style=social"/> : Object Detection API Tensorflow. (Other Versions of YOLO)

README

        
# Object-Detection-API-Tensorflow

# Features

## Every model is implemented in only one file!

# Models

Yolo2

Yolo3

SSD

RetinaNet

RefineDet

Light Head Rcnn

PFPNet

CenterNet

FCOS

# Train your own data

# Train your own data

## 1. TFRecord generation

1) voc format dataset

2) fill in utils.voc_classname_encoder.py

3) run utils.test_voc_utils.py

## 2. config online image augmentor

fill in dict 'image_augmentor_config' in test-model.py

see utils.image_augmentor.py for details

see https://github.com/Stick-To/Online_Image_Augmentor_tensorflow for details

## 3. config model

fill in dict 'config' in test-model.py

## 4. Train

run test-model.py

The pre-trained vgg_16.ckpt could be downloaded from http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz

## 5. Test

run annotated code in test-model.py

## 6. ImageNet pretraining

see utils.tfrecord_imagenet_utils.py

## 7. different conv backone

https://github.com/Stick-To/Deep_Conv_Backone

## 8. Instantiation of result 

 corresponding repository in https://github.com/Stick-To

 

# Experimental Environment

python3.7 tensorflow1.13