Inspiration
Urge to learn and practice projects in deep learning.
What it does
In this project, we have developed an image emotion classifier that uses deep learning techniques to determine whether an image is happy or sad. This classifier can be useful in a variety of applications, from social media sentiment analysis to market research.
How we built it
In this project, we have utilized the power of TensorFlow Keras API to develop a Convolutional Neural Network (CNN) model that is capable of recognizing the emotions of an image. We have trained the model using a dataset of happy and sad images to teach it to distinguish between the two emotions.
To preprocess the images, we have utilized OpenCV, an open-source computer vision and machine learning software library. OpenCV has helped us to load, resize and normalize the images before they are passed to the CNN model for training.
The CNN model consists of several convolutional and pooling layers followed by a fully connected layer that outputs a binary classification result - whether the image is happy or sad. We have used the rectified linear unit (ReLU) activation function to introduce non-linearity in the model, and dropout layers to avoid overfitting.
Challenges we ran into
Initially that data wasn't cleaned properly. So I had to clean the data.
Accomplishments that we're proud of
Successfully trained a CNN model.
What we learned
A lot about data handling and image processing.
What's next for Image Emotion Classifier.
Choosing a more rigorous DL model to classify more emotions.
Log in or sign up for Devpost to join the conversation.