Learn practical skills, build real-world projects, and advance your career


In this Deep Neural Network project, I have trained a ResNet-n (n=9) neural networks architecture with a different layers to classify a diverse set of 285 Bird Species from the Kaggle dataset with over 95.81% accuracy. For this project, I used the Kaggle 285 Birds Species Dataset, which consists of 285 bird species. 40930 training images, 1425 test images(5 images per species) and 1425 validation images(5 images per species. All images are 224 X 224 X 3 color images in jpg format. Data set includes a train set, test set and validation set. However the dataset is evolving and every month new bird species images are added.

!pip install jovian --upgrade --quiet

Let's begin by installing and importing the required libraries.

!pip install opendatasets --upgrade --quiet
import opendatasets as od