Skip to content

codistro/birds-species-identifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

birds-species-identifier

alt text

An End to End deep learning project for identifying 250+ bird species. React is used for frontend and flask as backend PyTorch is used for training the deep-learning model

Dataset

Dataset is taken from kaggle, which has 275 species dataset.

Training

ResNet-50 model is trained on Google colab pro which is implemented in PyTorch deep learning framework.

Achieved 99.9% accuracy on trainig set and 97.1% on test set, there is a chance of imrovement by adding data augmentation. It is observed that model struggle to identifies birds with front profiles.

About

An End to End deep learning project for identifying 250+ bird species. React is used for frontend and flask as backend PyTorch is used for training the deep-learning model

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors