Each project comes with 2-5 hours of micro-videos explaining the solution.
Code & Dataset
Get access to 50+ solved projects with iPython notebooks and datasets.
Add project experience to your Linkedin/Github profiles.
Understanding the problem statement
What is image masking
Importing the dataset
Initializing necessary libraries and understanding its use
Installing Tensorflow and Keras framework
Fetching masked and non-masked images and visualizing them
Performing Data augmentation for increasing the dataset
Colour transformation and Random Channel shift
Changing color scheme, Brightness, and Saturation
Drawing boxes around desired images
Visualizing the difference using plots
Performing Fast run image encoding on provided masked data
Training the Neural Networks
Running the Trained neural networks and fetching masked images as output
Using RLE to measure the accuracy of the model
Saving the final output
About the Carvana Image Masking Challenge Neural Network Project:
As with any big purchase, full information and transparency are key. While most everyone describes buying a used car is frustrating, it’s just as annoying to sell one, especially online. Shoppers want to know everything about the car but they must rely on often blurry pictures and little information, keeping used car sales a largely inefficient, local industry.
Carvana, a successful online used car startup, has seen an opportunity to build long term trust with consumers and streamline the online buying process.
An interesting part of their innovation is a custom rotating photo studio that automatically captures and processes 16 standard images of each vehicle in their inventory. While Carvana takes high-quality photos, bright reflections, and cars with similar colors as the background cause automation errors, which requires a skilled photo editor to change.
To develop an algorithm that automatically removes the photo studio background. This will allow
Carvana to superimpose cars on a variety of backgrounds. You’ll be analyzing a dataset of photos,
covering different vehicles with a wide variety of year, make, and model combinations.