Explore the fundamentals of tensors in this 29-minute video tutorial, part of the PyTorch with GPU series. Discover four different methods for initializing tensors in PyTorch, learn how to move tensors to CUDA/GPU, and master various tensor operations including arithmetic, slicing, and indexing. Gain insights into the shared memory locations between CPU tensors and NumPy arrays, and get introduced to PyTorch's Profiler context manager for performance optimization. Perfect for those looking to enhance their understanding of tensor manipulation and GPU acceleration in PyTorch.
Overview
Syllabus
Intro
Initializing a tensor 4 different ways in PyTorch!
Moving pytorch tensor to cuda / gpu
Operations on Tensor arithmetic, slicing, indexing
Tensors on CPU and numpy arrays can share their memory locations!
PyTorch's Profiler context manager
Taught by
Samuel Chan
Related Courses
-
Deep Learning - Computer Vision for Beginners Using PyTorch
-
PyTorch for Deep Learning & Machine Learning – Full Course
-
Everything You Need to Know About Tensors in Deep Learning With PyTorch
-
PyTorch Datasets, DataLoaders and Transforms - GPU Series Part 3
-
Mastering PyTorch Tensors- The Ultimate Guide for Beginners
-
Create a Large Language Model from Scratch with Python – Tutorial
