Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
S
SVLT
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Service Desk
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
ALMF
SVLT
Graph
17d129e6643e7bea20b521b69a7315fa62ecd4e5
Select Git revision
Branches
6
37-unnecessary-for-loop-in-rois-features
dev-nda-stream
dev_patch_viz
master
default
protected
migrate_model_server
staging
protected
Tags
4
2024.10.01
2024.06.03
2024.04.19
2024.03.01
10 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
20
Dec
19
13
Nov
10
7
6
3
2
31
Oct
30
27
26
25
22
20
19
18
17
16
14
13
12
11
10
9
8
5
29
Sep
28
27
26
25
13
12
7
6
5
4
1
31
Aug
30
29
28
24
23
22
Test covers instance segmentation base class
Implemented but did not yet test adding object classification result to RoiSet dataframe
Adapted base segmentation worklow and API endpoint for generic semantic segmentation model; made dummy model this type too
Test and example notebook that covers object classification from binary segmentation
Retained object classification from pixel probabilitie
Updated ilastik tests to cover semantic and instance segmentation methods
Added superclass for instance segmentation models and modified ilastik object classification to inherit from it
Added superclass for semantic segmentation models and modified ilastik pixel classification to inherit from it
Added superclass for semantic segmentation models and modified ilastik pixel classification to inherit from it
Renamed ZMask to RoiSet, prototyped object classification methods that add classification result as a dataframe column
Trying to test with batch operation but currently these do not involve object classification
Delegated export of patch products to ZMaskObjectTable class; consolidated both batch runner and API-facing workflows into infer_object_map_from_zstack(); consolidated parameterization of export products into pydantic model
Batch script to generate coloring book-like line profiles from pixel classifier
Merged in mask export method
Automatically export boolean masks as 0-255 black/white
Automatically export boolean masks as 0-255 black/white
Automatically export boolean masks as 0-255 black/white
Wait for confirmation that server is online before opening browser
Wait for confirmation that server is online before opening browser
only return keepers in zmask dataframe
Batch method for multi-chunk Ecotaxa TSV
Implemented batch export chunking
A few workarounds with zero-length patch sets
Ran two more porto sets through pipeline
Added pixel scale to CSV and Ecotaxa export
Corrected argument-forwarding error; set up job for porto data; split off ecotaxa TSV generation into its own module
Merge branch 'master' of git.embl.de:rhodes/model_server
Updated to new test classifiers
Updated to new test classifiers
Added docstrings
Moved client code back into repo; items in imagej directory won't run in server environment
Client now outside the server repo
Model-loading always returns {'model_id': _} when successfuly
Model-loading always returns {'model_id': _} when successfuly
Validated non-duplication when loading ilastik model with same project file name, irrespective of path formatting
Validated non-duplication when loading ilastik model with same project file name, irrespective of path formatting
Anything that creates a model returns the model_id as a string
Repair automatic session restart, which was causing test client problems; corrected return value of model query
Test covers problem with models being duplicated because of different path specifications; not yet fixed at API level
Need to explicitly restart session to clear persistent paths and models
Loading