Skip to content

Using neural network models trained on Tensorflow for inference, only using Opencv.

Notifications You must be signed in to change notification settings

ommmishra/opencv-dnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

opencv-dnn

The model used here is Tenorflow-lite model(ssdlite_mobilenet_v2_coco) from the tensorflow detection model zoo. To use the pre-trained model with opencv, we first need an extra configuration file to import object detection models from TensorFlow. It's based on a text version of the same serialized graph in protocol buffers format (protobuf). The script is included in the confGen folder. The script included here is for the models trained using the SSD architecture.

For more information and how to generate the config file do check the official Opencv implementation:
https://github.com/opencv/opencv/wiki/TensorFlow-Object-Detection-API

Model Link:
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

References:
https://www.pyimagesearch.com/2017/09/18/real-time-object-detection-with-deep-learning-and-opencv/
https://github.com/rdeepc/ExploreOpencvDnn/

About

Using neural network models trained on Tensorflow for inference, only using Opencv.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages