Car or Not a Car

Fine tuning has been shown to be very effective in certain types of neural net based tasks such as image classification. Depending upon the dataset used to train the original model, the fine-tuned model can achieve a higher degree of accuracy with comparatively less data. Therefore, we have chosen to fine tune ResNet50 pre-trained on the ImageNet dataset provided by Google.

We are going to explore ways to train a neural network to detect cars, and optimise the model to achieve high accuracy. In technical terms, we are going to train a binary classifier which performs well under real-world conditions.

There are two possible approaches to train such a network:

To train from scratch, we need a lot of data — millions of positive and negative examples. The process doesn’t end at data acquisition. One has to spend a lot of time cleaning the data and making sure it contains enough examples of real world situations that the model is going to encounter practically. The feasibility of the task is directly determined by the background knowledge and time required to implement that.

Basic Setup

There are certain requisites that are going to be used throughout the exploration:

Experiment 1

To start with a simple approach, we take ResNet50 without the top layer and add a fully connected (dense) layer on top of it. The dense layer contains 32 neurons which are activated with sigmoid activator. This gives approximately 65,000 trainable parameters which are plenty for the task at hand.

Related posts:

Are humans divisive in nature? Is it in our genes and in the very core of our behavioral dynamics that we look for fissures and friction where they need not be? Perhaps, yes. Because looking at the…

The term Thoughts of the Day means daily quote that ensures position vibes to start your day. These thoughts assist you to get inspired so that you can begin your day with a big smile. Today, we have…

One of our objectives at Contrast VR is to share our content with as many people as possible, focusing on a global audience. We believe that our stories shouldn’t live exclusively on headsets, but…