This project uses Convolutional Neural Networks (CNNs)! In this project, you will learn how to build a pipeline to process real-world, user-supplied images. Given an image of a dog, your algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.
Step 0: Import Datasets Step 1: Detect Humans Step 2: Detect Dogs Step 3: Create a CNN to Classify Dog Breeds (from Scratch) Step 4: Use a CNN to Classify Dog Breeds (using Transfer Learning) Step 5: Create a CNN to Classify Dog Breeds (using Transfer Learning) Step 6: Write your Algorithm Step 7: Test Your Algorithm
We need a lot of different data to solve this problem, let’s start by downloading them:
- Dog Images
- Human Images
- ResNet50 Features
- OpenCV Human Face Detection Model
Please see detailed analysis of project in my blog post . Linl is mentioned here: https://medium.com/@pranjalvijaykota/dog-breed-classification-eae5c28afef1
This is Dog breed classification project is build in CNN -Convolution neural networks. This app wil give an identify an estimate of any image given by user as input , that if it is a dog image or a human image or neither human nor dog. Then if it is a dog image it give the estimate that of which breed this canine belongs to. And if it is a human image the will give the guess of which dog breed this human resembles to. And if an image is not of an human or a dog then it gives result as “This is neither a dog nor a human.”