Inspiration
This app has been inspired by my experience with plants and flowers and interest in their classification.
What it does
It takes sepal width, height and petal width, height and classifies the flower into two categories based on two parameters.
How we built it
I used a backpropagation algorithm with sigmoid function as an activation function. The neural net consists of 3 layers, one input layer of 4 nodes, one hidden layer of 6 nodes and an output layer of one node.
Challenges we ran into
Learning neural networks, implementing backpropagation algorithm, learning to use the libraries for the same.
Accomplishments that we're proud of
Being able to successfully classify the images according to the given parameters.
What we learned
To use numpy, pandas and other relevant libraries, neural networks and their algorithms.
What's next for flower detector
Expanding it to flowers other than iris setosa and iris versicolor and also detecting if there may be abnormalities in the flowers based on the data.
Log in or sign up for Devpost to join the conversation.