Auto Added by WPeMatico
Escnn, built on PyTorch, is a library that, in the spirit of Geometric Deep Learning, provides a high-level interface to designing and training group-equivariant neural networks. This post introduces important mathematical concepts, the library’s key actors, and essential library use.
Group-equivariant neural networks with escnn Read More »
We train a model for image segmentation in R, using torch together with luz, its high-level interface. We then JIT-trace the model on example input, so as to obtain an optimized representation that can run with no R installed. Finally, we show the model being run on Android.
Train in R, run on Android: Image segmentation with torch Read More »
We code up a simple group-equivariant convolutional neural network (GCNN) that is equivariant to rotation. The world may be upside down, but the network will know.
Implementing rotation equivariance: Group-equivariant CNN from scratch Read More »
Currently, in generative deep learning, no other approach seems to outperform the family of diffusion models. Would you like to try for yourself? If so, our torch implementation of de-noising diffusion provides an easy-to-use, easy-to-configure interface.
De-noising Diffusion with torch Read More »
In forecasting spatially-determined phenomena (the weather, say, or the next frame in a movie), we want to model temporal evolution, ideally using recurrence relations. At the same time, we’d like to efficiently extract spatial features, something that is normally done with convolutional filters. Ideally then, we’d have at our disposal an architecture that is both
Convolutional LSTM for spatial forecasting Read More »
El Niño-Southern Oscillation (ENSO) is an atmospheric phenomenon, located in the tropical Pacific, that greatly affects ecosystems as well as human well-being on a large portion of the globe. We use the convLSTM introduced in a prior post to predict the Niño 3.4 Index from spatially-ordered sequences of sea surface temperatures.
Forecasting El Niño-Southern Oscillation (ENSO) Read More »
A couple of months ago, Amazon, Facebook, Microsoft, and other contributors initiated a challenge consisting of telling apart real and AI-generated (“fake”) videos. We show how to approach this challenge from R.
Deepfake detection challenge from R Read More »
We learn about transfer learning, input pipelines, and learning rate schedulers, all while using torch to tell apart species of beautiful birds.
Classifying images with torch Read More »
The need to segment images arises in various sciences and their applications, many of which are vital to human (and animal) life. In this introductory post, we train a U-Net to mark lesioned regions on MRI brain scans.
Brain image segmentation with torch Read More »
In image segmentation, every pixel of an image is assigned a class. Depending on the application, classes could be different cell types; or the task could be binary, as in “cancer cell yes or no?”. Area of application notwithstanding, the established neural network architecture of choice is U-Net. In this post, we show how to
Image segmentation with U-Net Read More »
