Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
A
aidge_export_tensorrt
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Deploy
Releases
Model registry
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Nathan Thoumine
aidge_export_tensorrt
Commits
c977243b
Commit
c977243b
authored
1 year ago
by
Nathan Thoumine
Browse files
Options
Downloads
Patches
Plain Diff
add general graph class description
parent
91dbf3e2
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
aidge_export_tensorrt/static/tensorrt_8.6/include/Graph.hpp
+9
-0
9 additions, 0 deletions
aidge_export_tensorrt/static/tensorrt_8.6/include/Graph.hpp
with
9 additions
and
0 deletions
aidge_export_tensorrt/static/tensorrt_8.6/include/Graph.hpp
+
9
−
0
View file @
c977243b
...
...
@@ -32,6 +32,15 @@ typedef struct
unsigned
int
nIO
;
}
IOGraphDesc
;
/**
* @class Graph
* @brief Manages the lifecycle and execution of a neural network graph using TensorRT.
*
* The Graph class encapsulates the functionality required to manage, configure, and execute
* a neural network graph for inference using NVIDIA's TensorRT. This includes loading models
* from ONNX or TensorRT files, setting the CUDA device and data types, managing calibration
* for INT8 precision, and running inference in both synchronous and asynchronous modes.
*/
class
Graph
{
public:
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment