Everybody who watched ‘Minority Report’ daydreams about crime forecasting in the real world. We have good news: machine learning algorithms can do that!
In this post we present how to approach product recognition through the example of our solution for the iMaterialist challenge announced by CVPR and Google.
In this post we show a way to run machine learning experiments with distributed TensorFlow on Slurm clusters. A simple CIFAR-10 example is also included.
Despite recent advances in deep learning, the way mathematics is done today is still much the same as it was 100 years ago. Isn’t it time for a change?
In the previous post we explained what region of interest pooling (RoI pooling for short) is. In this one, we present an example of applying RoI pooling in TensorFlow. We base it on our custom RoI pooling TensorFlow operation. We also use Neptune as a support in our experiment performance tracking.
At the end of April 2017, deepsense.ai released a new version of Neptune, the DevOps platform for data scientists. Neptune 1.5 introduces a range of new features and improvements, including support for Python 3, simplification of Neptune CLI, offline execution, …
We describe 4th place solution based on image segmentation and deep learning for Dstl Satellite Imagery Feature Detection competition.
We present the training of an XGBoost model and evaluation of the results in an example analysis of bank customer data, using R with Neptune.
In February we released a new version of Neptune, our machine learning platform for data scientists, supporting them in more efficient experiment management and monitoring. The latest 1.4 release introduces new features, like grid search — a hyperparameter optimization method and support for R and Java programming languages. Grid Search The first major feature introduced […]
Region of interest pooling (also known as RoI pooling) is an operation widely used in object detection tasks using convolutional neural networks. For example, to detect multiple cars and pedestrians in a single image. Its purpose is to perform max pooling on inputs of nonuniform sizes to obtain fixed-size feature maps (e.g. 7×7). We’ve just […]