Statements (93)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:physicist
gptkb:Library |
| gptkbp:bfsLayer |
3
|
| gptkbp:bfsParent |
gptkb:CUDA
|
| gptkbp:api |
Python API
C++ API CAPI |
| gptkbp:developed_by |
gptkb:DJ
|
| gptkbp:enhances |
inference speed
training speed |
| gptkbp:has |
gptkb:API
|
| https://www.w3.org/2000/01/rdf-schema#label |
cu DNN
|
| gptkbp:improves |
memory efficiency
|
| gptkbp:includes |
tensor operations
|
| gptkbp:integrates_with |
gptkb:Graphics_Processing_Unit
gptkb:Caffe gptkb:Py_Torch MX Net |
| gptkbp:is |
cross-platform
open source widely used used in finance used in research used in robotics designed for flexibility used in production available for Windows designed for performance integrated into cloud services part of AI frameworks designed for scalability highly optimized used in healthcare applications used in autonomous vehicles available for Linux available for mac OS part of NVIDIA Deep Learning SDK |
| gptkbp:is_available_for |
free download
|
| gptkbp:is_available_on |
gptkb:smartphone
gptkb:operating_system |
| gptkbp:is_compatible_with |
gptkb:CUDA
|
| gptkbp:is_documented_in |
NVIDIA documentation
|
| gptkbp:is_optimized_for |
gptkb:NVIDIA_Ampere_architecture
gptkb:NVIDIA_Turing_architecture gptkb:NVIDIA_Volta_architecture gptkb:NVIDIA_Pascal_architecture NVIDIAGP Us |
| gptkbp:is_part_of |
gptkb:NVIDIA_Deep_Learning_SDK
NVIDIAAI platform NVIDIA Deep Learning Frameworks |
| gptkbp:is_supported_by |
NVIDIA developer community
|
| gptkbp:is_tested_for |
NVIDIAGP Us
|
| gptkbp:is_used_for |
deep learning
natural language processing reinforcement learning image classification object detection |
| gptkbp:is_used_in |
gptkb:film_production_company
gptkb:Research_Institute |
| gptkbp:latest_version |
8.0
8.6.0 |
| gptkbp:license |
NVIDIA End User License Agreement
|
| gptkbp:offers |
automatic tuning
|
| gptkbp:performance |
gptkb:microprocessor
deep learning models |
| gptkbp:provides |
profiling tools
activation functions multi-GPU support automatic differentiation high-performance primitives normalization functions pooling functions |
| gptkbp:released_in |
gptkb:2014
|
| gptkbp:requires |
gptkb:CUDA_Toolkit
|
| gptkbp:supports |
deep learning frameworks
convolutional neural networks activation functions mixed precision training multi-GPU training convolution operations normalization layers RN Ns F P16 precision GR Us IN T8 precision LST Ms mixed precision pooling operations |
| gptkbp:updates |
gptkb:battle
|
| gptkbp:used_in |
machine learning applications
deep learning frameworks training neural networks |
| gptkbp:written_in |
gptkb:C++
|