courseraАнализ данных

Optimize PyTorch: Build and Accelerate Layers

Курс от Coursera

Средний≈ 2.6 чАнглийский

О курсе

Learn to build custom neural-network layers and accelerate model training with performance-driven PyTorch techniques. This hands-on, engineer-focused course teaches you how to design differentiable modules, diagnose bottlenecks, and apply optimizations like mixed precision and gradient accumulation to significantly boost training throughput.

Навыки, которые вы освоите

Model Optimization PyTorch (Machine Learning Library)Performance Analysis Artificial Neural Networks Deep Learning Resource Utilization Model Training

Программа курса

1 модулей · 15 учебных материалов

01Optimize PyTorch: Build and Accelerate Layers15 материалов

Custom Layers in PyTorch: From Building Blocks to Squeeze-and-Excite

Why Build Custom Layers in PyTorch? DIALOGUE Why Custom Layers Matter in PyTorchВидео Tensor Operations & Autograd: How PyTorch Tracks Your ComputationsВидео How PyTorch Tracks Your ComputationsЧтение

Учитесь у экспертов

Professionals in the Industry

ansrsource instructors