CV-Tricks stands for computer vision tricks. In this blog, we write about the practical tips, tricks, and methods used for making world-class computer vision solutions. We believe that computer vision is still in its infancy and increasingly computer vision is going to be embedded into most of our systems. Cars and drones are just a beginning. As any sane computer vision practitioner, We are very bullish on artificial intelligence/deep learning, so we are going to cover a lot of TensorFlow and Caffe which are our primary weapons of choice. But we also understand that a lot of systems don’t have GPUs so we also write content around openCV, DLIB based computer vision solutions.
For any suggestions, ideas or feedback, do reach out to us at firstname.lastname@example.org
People behind CV-Tricks:
Koustubh is an expert in Deep Learning technology with extensive experience in Deep Learning frameworks like Caffe and Tensorflow. He’s an alumnus of IIT Kanpur, India’s premier engineering institute with an acceptance rate of < 2%. You can connect with him on LinkedIn.
Ankit Sachan is an expert in building scalable Deep Learning solutions using popular libraries like Tensorflow. He’s also a Google Developer Expert(GDE) in Machine Learning. He received his Bachelor of Technology degree from the prestigious Indian Institute of Technology, Kanpur. He can be reached on LinkedIn or Twitter.
Both Ankit and Koustubh co-founded iLenze, a computer vision and deep learning company that built visual search systems for lifestyle and fashion. Today, we run AIMonk, deep learning and machine learning platform specialized in computer vision building next-generation products and features using AI. If you are solving any interesting problem using Deep Learning and computer vision, do reach out to us at email@example.com.
If you have a deep learning project where you have 70-80% accuracy but you are struggling to push the accuracy to production level, you must check out our data annotation and management platform NeuralMarker. In the last 5 years, we have seen dozens of Deep Learning projects which made into production. Every time, we were able to push the models in production, we always followed a more or less similar process. It had more to do with training data than the algorithm. It was always painful and involved us getting our hands dirty in the dataset. NeuralMarker is our attempt to bake all those learnings and best practices in a platform so that AI teams developing computer vision solutions can deliver production-quality model more reliably and rapidly.