Introduction to PyTorch

By Nikhil S. Ketkar. Deep Learning with Python, 2021

616 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/be0c539bec5c2d379ab1884e61a5bb8ccb91dc30

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Video Instance Segmentation Tracking With a Modified VAE Architecture (2020, methodology): “We implement our model in PyTorch [26] and train it with 4 GeForce RTX 2080 Ti GPUs.”
Learning to Learn: Hierarchical Meta-Critic Networks (2019, methodology): “All the networks were built and trained in Pytorch [35].”
Graph Representation Learning via Graphical Mutual Information Maximization (2020, methodology): “All experiments are implemented in PyTorch [23] with Glorot initialization [13] and conducted on a single Tesla P40 GPU.”
A Deep Residual Network for Large-Scale Acoustic Scene Analysis (2019, methodology): “All networks were trained with the Pytorch framework [27], using the Adam optimizer [28], with a learning rate of 0.”
Deep learning for smart fish farming: applications, opportunities and challenges (2020, methodology): “In particular, because of its strong support for graphical processing unit (GPU), the PyTorch framework has been used extensively in relatively recent literature (Ketkar, 2017 ; Liu et al., 2019).”
SparCML: High-Performance Sparse Communication for Machine Learning (2018, neutral): “Virtually all major frameworks optimize for efﬁcient communication [1, 10, 28, 42, 53], while GPU vendors are developing speciﬁc communication layers for this goal [37].”
An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications (2019, methodology): “Libraries such as Tensorflow [5] and PyTorch [6] provide the building blocks to devise learning machines for very different problems.”