UppuluriKalyani · SaiNivedh26 · Oct 4, 2024 · Oct 4, 2024
diff --git a/Neural Networks/Bird Species Classification/Dataset/Readme.md b/Neural Networks/Bird Species Classification/Dataset/Readme.md
@@ -0,0 +1,7 @@
+- The link for the dataset used in this project: https://www.kaggle.com/datasets/veeralakrishna/200-bird-species-with-11788-images
+
+- Caltech-UCSD Birds-200-2011 (CUB-200-2011) is an extended version of the CUB-200 dataset, with roughly double the number of images per class and new part location annotations. 
+
+- Number of categories: 200
+
+- Number of images: 11,788
diff --git a/Neural Networks/Bird Species Classification/Images/EfficientNetB0.png b/Neural Networks/Bird Species Classification/Images/EfficientNetB0.png
diff --git a/Neural Networks/Bird Species Classification/Images/InceptionV3.png b/Neural Networks/Bird Species Classification/Images/InceptionV3.png
diff --git a/Neural Networks/Bird Species Classification/Images/inception_resnet_v2 .png b/Neural Networks/Bird Species Classification/Images/inception_resnet_v2 .png
diff --git a/Neural Networks/Bird Species Classification/Images/masked_image_1.png b/Neural Networks/Bird Species Classification/Images/masked_image_1.png
diff --git a/Neural Networks/Bird Species Classification/Images/masked_image_2.png b/Neural Networks/Bird Species Classification/Images/masked_image_2.png
diff --git a/Neural Networks/Bird Species Classification/Images/masked_image_3.png b/Neural Networks/Bird Species Classification/Images/masked_image_3.png
diff --git a/Neural Networks/Bird Species Classification/Model/bird_species_classification.ipynb b/Neural Networks/Bird Species Classification/Model/bird_species_classification.ipynb
diff --git a/Neural Networks/Bird Species Classification/Readme.md b/Neural Networks/Bird Species Classification/Readme.md
@@ -0,0 +1,49 @@
+**Bird Species Classification**
+
+This repository contains a bird species classification project that uses deep learning models such as EfficientNetB0, InceptionResNetV2, InceptionV3, and VGG16 to identify and classify different bird species from images. The project aims to achieve accurate bird species classification using state-of-the-art Convolutional Neural Networks (CNNs) for image recognition tasks.
+
+
+**Overview**
+
+Bird species classification is an important task for various applications, including wildlife monitoring, ecological research, and conservation efforts. This project implements several advanced deep learning architectures to classify images of birds into different species.
+
+We have experimented with different CNN architectures:
+
+	•	EfficientNetB0: A highly efficient model designed to achieve high accuracy with low computational power.
+	•	InceptionResNetV2: A hybrid architecture that combines Inception modules and residual connections.
+	•	InceptionV3: An earlier version of the Inception network that uses factorized convolutions for computational efficiency.
+	•	VGG16: A classical deep learning architecture that uses 16 layers to achieve strong performance in image classification tasks.
+
+**Models Used**
+
+The project utilizes the following models for bird species classification:
+
+	1.	EfficientNetB0:
+        •	Known for its balance between accuracy and efficiency.
+        •	Pretrained on the ImageNet dataset.
+	2.	InceptionResNetV2:
+        •	Combines the strengths of Inception and ResNet architectures.
+        •	Highly accurate for image classification.
+	3.	InceptionV3:
+        •	Uses factorized convolutions to reduce computation.
+        •	Pretrained on ImageNet.
+	4.	VGG16:
+        •	A classic architecture with a simple and uniform layer structure.
+        •	Known for its depth and strong feature extraction capabilities.
+
+
+Dataset
+
+The dataset used in this project consists of bird species images. It includes:
+
+	•	High-resolution images of various bird species.
+	•	Images gets separated in properly labeled dataset with training, validation, and test splits during the preprocessing.
+
+Link : https://www.kaggle.com/datasets/veeralakrishna/200-bird-species-with-11788-images
+
+
+License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.
+
+Feel free to reach out if you have any questions or suggestions!