The project goal is an image classification problem for deep learning models. So I explored a simple neural network, and then progressed to convolutional neural network and transfer learning. First I started with image classification using a Simple Neural Network. The dataset is from pyimagesearch, which has 3 classes: cat, dog, and panda. There are 3000 images in total, ie, 1000 for each class. Then I studied the Convolutional Neural Network, where each image goes through a series of convolution and max pooling for features extraction. I explored using the CIFAR-10 dataset which has 60,000 images divided into 10 classes. Next I explored a huge dataset of over a million images, using Transfer Learning to avoid reinventing the wheel. I used the VGG16 pre-trained model developed by University of Oxford, which has 1000 classes ranging from animals to things and food. The conclusion is: Image classification can be done using neural network models. Identifying patterns and extracting features on images are what deep learning models can do, and they do it very well. More details on this project: Medium: medium.com/analytics-vidhya/image-classification-using-artificial-neural-network-61637c7c6f9f Github: https://github.com/JNYH/Project_Kojak
1. Get feedback on your portfolio projects from fellow techies and makers.
2. Free 3 months subscription to Crash to pitch top companies.
3. Access Career Karma Hiring Assessment powered by Triplebyte to introduce top bootcamp students to remote friendly tech companies.
4. Portfolio Projects Masterclass Workshops.