Average internet user now spends 6 hours and 40 minutes a day using the internet.
While there are many apps dealing with harmful content, each user has his own personal preferences and definition for unwanted content.
Project Goal
• Build an application that will allow internet users to filter-out unwanted images based on their preference, in a simple and comfortable way.
Transfer learning is a method where a model that has been previously trained on a dataset and contains the weights and biases can be used again.
Use cropped faces images improves networks accuracy in almost 20%.
• The results we got on the test set were better than the results we got on “production” – excellent accuracy on the test set is not reflected on images from the web pages.
• Transfer learning is an easy and efficient way for fine tuning pre-trained CNN and use it for our purposes.