Skip to content

Custom Object Detection Using Tensorflow Object Detection API using pre trained ssd_mobile_net model . Downloaded the model from object detection module of tensorflow and then further customized it to build my own cctv camera using opencv's Video capture to determine the exact date and time when an object was detected.

Notifications You must be signed in to change notification settings

meenakshisharma2367/Custom-Object-Detection-Using-Tensorflow-Object-Detection-API

Repository files navigation

tensorflow-object-detection-api-configuration

This tutorial discusses how to configure the Tensorflow Object Detection API in windows and how implement custom object detection.

Credits & Links

  1. Download Tensorflow Object Detection API
  2. How to install Tensorflow Object Detection

Installing the Tensorflow Object Detection API

  1. Download the tensorflow object detection api from Github
  2. Open the Anaconda Prompt and install the dependencies for windows,
pip install tensorflow
pip install Cython
pip install contextlib2
pip install pillow
pip install lxml
pip install jupyter
  1. Download the files from this repository
  2. Copy and paste protoc.exe file in the path models-master\research
  3. Open the Commmand Prompt in models-master\research and copy and run the command included in protoc command.txt
  4. Copy the files object_detection_tutorial.ipynb, 1.0 Customized Object Detection.ipynb & 1.1 Customized Object Detection-Video.ipynb into models-master\research
  5. Run above codes and check

Models used in Tensorflow Object Detection API

Models used in Tensorflow Object Detection API

About

Custom Object Detection Using Tensorflow Object Detection API using pre trained ssd_mobile_net model . Downloaded the model from object detection module of tensorflow and then further customized it to build my own cctv camera using opencv's Video capture to determine the exact date and time when an object was detected.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published