NVIDIA Deep Learning SDK Documentation - Last updated June 26, 2020 - Send Feedback -

NVIDIA Deep Learning SDK

Introduction To Deep Learning SDK
The two major operations from which deep learning produces insight are training and inference. While similar, there are significant differences. Training, feeds examples of objects to be detected/recognized like animals, traffic signs, etc., allowing it to make predictions, as to what these objects are. The training process reinforces correct predictions and corrects the wrong ones. Once trained, a production neural network can achieve upwards of 90-98% correct results. "Inference", is the deployment of a trained network to evaluate new objects, and make predictions with similar predictive accuracy. Inference comes after training, therefore, you must obtain a trained neural network before you can perform inference.

Training Library

cuDNN Support Matrix
These support matrices provide a look into the supported versions of the OS, CUDA, the CUDA driver, and the NVIDIA hardware for the cuDNN 8.0.1 Preview Release and earlier releases.
cuDNN Release Notes
NVIDIA CUDA Deep Neural Network (cuDNN) is a GPU-accelerated library of primitives for deep neural networks. It provides highly tuned implementations of routines arising frequently in DNN applications. These release notes describe the key features, software enhancements and improvements, and known issues for the cuDNN 8.0.1 Preview Release and earlier releases.
cuDNN Installation Guide
This cuDNN 8.0.1 Preview Release Installation Guide provides step-by-step instructions on how to install and check for correct operation of cuDNN on Linux and Microsoft Windows systems.
cuDNN Developer Guide
This cuDNN 8.0.1 Preview Release Developer Guide provides an overview of cuDNN features such as customizable data layouts, supporting flexible dimension ordering, striding, and subregions for the 4D tensors used as inputs and outputs to all of its routines. This flexibility allows easy integration into any neural network implementation.
Best Practices For cuDNN
This Best Practices guide covers various 3D convolution and deconvolution guidelines. This document also provides guidelines for setting the cuDNN library parameters to enhance the performance for 3D convolutions in the cuDNN 8.0.1 Preview Release. Specifically, these guidelines are focused on settings such as filter sizes, padding and dilation settings.
cuDNN API Reference
This is the cuDNN 8.0.1 Preview Release API. This Preview release is for early testing and feedback, therefore, for production use of cuDNN, continue to use cuDNN 7.6.5. This Preview release is subject to change with performance tuning and functional testing ongoing. For feedback on the new backend API and deprecations, email cudnn@nvidia.com.
This document is the Software License Agreement (SLA) for NVIDIA cuDNN. The following contains specific license terms and conditions for NVIDIA cuDNN. By accepting this agreement, you agree to comply with all the terms and conditions applicable to the specific product(s) included herein.


cuDNN Archives
This Archives document provides access to previously released cuDNN documentation versions.