Skip to content

pulaksahoo/Transfer-Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Transfer-Learning

The project implements a technique called "Transfer Learning" using Imagenet pretrained models VGG19 or ResNet50. Get the pretrained model and verify the accuracy on the CPUs/GPUs. Take a new image data set like for example, fish data-set: http://groups.inf.ed.ac.uk/f4k/GROUNDTRUTH/RECOG/ Use the transfer learning technique to freeze a few layers of the pretrained models and retrain using the new data set Show the accuracy on the new data-set should be roughly equal to or more than original imagenet accuracy. Used TF framework

About

Transfer Learning using Imagenet pretrained models VGG19 and ResNet50. The pretrained model were used to verify the accuracy on the CPUs/GPUs and retrain them on a different set of data to reduce the learning time.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages