Draw2develop

It is a deep learning model which extract features and creates a HTML/CSS based single page website from components drawn on paper.

DESCRIPTION:

Technology used:

Basic Python:

1.Conditional statements 2.Loops 3.Libraries

Machine Learning:

1.Classification 2.Regression 3.Prediction

Deep learning:

1.Neural networks 2.CNN

Libraries used:

Pandas Tensorflow Keras

Activation Function:

Exponential Linear Unit (ELU): It is a function that tends to converge cost to zero faster and produce more accurate results. Different to other activation functions, ELU has a extra alpha constant which should be positive number.

Sigmoid: It is normally used to refer specifically to the logistic function, also called the logistic sigmoid function. All sigmoid functions have the property that they map the entire number line into a small range such as between 0 and 1, or -1 and 1.

Dataset:

we have provided more than 85 images to train the model which contains the Navigation Bar, Main-Section, Header and Footer.

Examples:

Model Graph:

Results:

val_loss=1.3

Model with balanced dataset: Model with less full images:

Test images Results:

Order of result:

Navbar - Sidebar - Footer - Main