Car detection 20170618

Last week, Google released an awesome tool for anyone who is interested in computer vision and deep learning. It is called “Tensorflow Object Detection API“.  There are many pre-trained models on it so we can perform computer vision tasks, such as classification and segmentation without waiting for a long time to complete. The images above is obtained in my Mac Air 11 according to tutorials here. It looks awesome. It does not take too much time to calculate as the pre-trained model is available in the API.

I would like to explain why Object Detection API is awesome

1. It has major classification models.

 

 

2. It enables us to  combine classification models with object detections framework

 

 

 

 

 

 

Car detection 20170617

3. It can be run locally and Google Cloud Platform

 

I try one of them to the images I have. It looks good. This can be our framework for experiments as there are many pre-trained models in it. I will go deeper for a while.

Cheers Toshi

 

 

https://github.com/tensorflow/models/tree/master/object_detection

 

 

Advertisements

This is one of the greatest tools I have ever seen. Thanks Google!

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s