By Vadim Frolov, Data Scientist at Inmeta
Neural networks (NN) and computer vision models in particular are known to perform well in specific tasks, but often fail to generalize to tasks they have not been trained on. A model that performs well on a food data may perform poorly on satellite images.
A new model from OpenAI named CLIP claims to close this gap by a large margin. The paper Open AI wrote presenting CLIP demonstrates how the model may be used on a various classification datasets in a zero-shot manner.
In this article, I will explain the key ideas of the model they proposed and show you the code to use it. …
By Anna Rabstad, Service and UX designer at Inmeta
When you have done your research, how do you make sense of it? You probably want to extract some insights from the research, but how? This is a short introduction to what insights is, and how to discover them.
This article was born after I did a short talk on this topic at Pecha Kucha Night in Hamar for a limited audience and was afterwards challenged to embroider it further. Why not? — was my thought and here we go.
Welcome to a short introduction to insights, what it is in a context of service or product design and what it takes to uncover great insights. Disclaimer, all characters are fictious and any similarities with real life are a matter of coincidence. …
By Vadim Frolov, Data Scientist at Inmeta
With ML projects still on the rise we are yet to see integrated solutions in almost every device around us. The need for processing power, memory and experimentation has led to machine learning and DL frameworks targeting desktop computers first. However once trained, a model may be executed in a more constrained environment on a smartphone or on an IoT device. A particularly interesting environment to run the model on is browser. Browser-based solutions may be used on a wide range of devices, desktop and mobile, online and offline. …
And why would you want to apply them in your machine learning projects.
By Greta Elvestuen, PhD, Data Scientist consultant at Inmeta
Throughout the last decade, convolutional neural networks (CNNs) have brought significant improvements in performance to machine learning models. Especially deep learning models have gained high popularity within the field of computer vision, due to their vast achievements and implementation in a wide variety of everyday applications.
However, training such networks is very time-consuming. Large datasets are necessary in order to train a high performing model, leading to excessive training times for up to several weeks. This is especially unfortunate in cases of testing how well the network is performing in order to make the necessary adjustments. …
About
