Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
M
macaon
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container Registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Franck Dary
macaon
Graph
4bebd4a82cf13e8c7cac23b8c062695d401549ee
Select Git revision
Branches
3
loss
master
default
protected
producer
3 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
25
Mar
24
23
21
20
16
12
7
6
5
4
3
2
1
22
Feb
20
19
17
16
12
11
10
9
8
7
6
5
20
Jan
19
17
15
8
4
7
Dec
17
Nov
16
30
Oct
26
23
22
16
14
9
10
Sep
9
16
Aug
11
7
6
5
4
31
Jul
30
28
15
14
9
7
2
1
30
Jun
29
26
23
22
21
19
18
17
16
15
14
13
12
10
9
8
7
5
4
3
2
28
May
25
24
23
21
18
17
16
15
14
13
12
11
10
8
6
5
4
3
30
Apr
29
27
26
24
23
22
21
20
17
16
15
14
13
12
11
10
9
8
7
6
5
3
2
1
31
Mar
30
29
26
21
20
19
17
16
15
14
12
11
10
9
8
7
5
4
3
2
28
Feb
27
26
25
24
23
22
21
20
19
17
16
15
14
13
12
11
8
7
6
5
4
31
Jan
30
29
28
27
26
22
21
20
14
13
12
9
8
7
6
2
21
Dec
20
19
18
17
16
15
14
13
12
11
Added sanity check when loading pretrained word embeddings
When constructing WordEmbedding, only use max_norm when necessary
Improved forcing EOS transition, usefull for lineByLine mode
Allow blank line to be commented in tsv
When loading optimizer, do not silently fail
Removed debug print
Removed warning
Added functions getDevice and setDevice
Added test for overflow
Fixed discrete features values
Added fmt as a submodule
Using bare std::string instead of flyweight because it caused datarace in some computers
Changed execution policy from par_unseq to par
Parallel extractExamples
Corrected bug in MacaonDecode where dicts were not closed. Parallel decode.
Macaon train decoding (devScore) on cpu in parallel
Parallel decoding for trainer (devScore)
Corrected bug where tensor was not initialized to the correct device
Made sure Dict never contained 2 elements with the same index
extractContext now directly gives a torch::Tensor
Removed state from neuralnetwork
Corrected wrong device error when using from_blob
Trying to load gpu tansor onto cpu mem
Added case for regression in extractExamples
Fixed oracles of non rel arc eager
Removed use of action setRootUpdateIdsEmptyIfSentChanged
Removing TSV lines from Config constructor when in txt mode
Added special columns STACK_SIZE et STACK_DIST
Added NA to default value in NumericColumnModule
Corrected problem where mcd was not propagated in lineByLine mode
Working lineByLine in tsv mode
Added lineByLine in train in tsv mode
Corrected bug in readTSV
Improved speed of readTSV
Fixed bug with splitword
Updated Transformer using pytorch module
Took care of some compiler warnings
Fixed unused parameter warnings
Added train option lineByLine
strongly typed enums
Loading