Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
aidge_core
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
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD 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
Cyril Moineau
aidge_core
Graph
b91f4448c33eff9707b707748bf8947ef9ef06b5
Select Git revision
Branches
20
Add_GlobalAveragePooling
ImproveRemoveFlatten
add_clipping_node
allowNoInputProducer
backend_export
copytape
createUniqueName
dataProvider_setBackend
dev
enable_custom_op
feat/DataTypes
feat/GraphInterpreter
feat/RefGetImpl
feat/SplitConv
feat/TensorCopy
feat/formatting
featTokenGraphRegex
fix
fixGraphRegexUnique
fixMain
Tags
5
v0.2.2
v0.2.1
v0.2.0
v0.1.1
v0.1.0
25 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
15
Feb
14
13
12
11
9
7
6
5
2
1
31
Jan
30
29
26
25
24
23
18
17
16
15
12
11
10
8
5
4
21
Dec
20
18
15
14
13
12
11
10
9
8
7
6
5
4
3
1
30
Nov
29
28
27
24
23
22
21
20
17
16
15
14
13
10
9
8
7
30
Oct
27
26
25
24
23
20
19
18
17
16
13
12
11
10
9
6
5
4
3
[Add] Scalar constructor for Tensor and int8 support
Merge branch 'dev' into broadcasting
Added Pop operator to handle sequences
Fixed parameter input for Memorize
Improved error and fixed possible segfault
Fixed Producers for LSTM
Improved error messages
[Fix] input unsqueeze during output dimensions computation process in MatMul_Op
Update tensorimpl_cpu with dimensions
Merge dev into dataloader
Update pybind_trensor with the ctr by dims instead of number of elements
Update TensorImpl constructor to take the tensor dimensions instead of the number of elements. Necessary for backend_opencv.
[Fix] 'keepDim' variable
Try system header
Refactor 'computeOutputDims()' member function of MatMul Operator to add dimensions broadcasting
Move two functions to Tensor src instead of header
Standardize code for MatMul.hpp and Test_TensorImpl.cpp
[Add] Test for 'computeOutputDims()' member function of MatMul Operator
Fix GCC 12 error
Switched fmt to header only
Use fmt library instead of custom functions, added GraphView::getRankedNodes() and GraphView::getRankedNodesName() methods
Added Python binding for new operators
Fixed typo
Fixed minor issues
Added LSTM meta-operator (not tested yet with actuel values)
minor fixes for matmul
fix python binding for matmul
minor cleanups
Merge branch 'vit_operators' into 'dev'
Merge branch 'dev' into matmul_rework
[Fix] set axis conversion to positive values in 'computeOutputDims()'
[WIP][NF] update ReduceMean
[Upd][WIP][NF] 'backward()' for SequentialScheduler
Fixed issues
Better suppress warning
Added output dims display in GraphView::save()
Added Tanh and Sigmoid operators
Improved error handling
Merge branch 'QualityOfLife' into 'dev'
Merge branch 'dev' into dataloader
Loading