Skip to content

continuous integration#78

Open
xiuliren wants to merge 167 commits into
masterfrom
ci
Open

continuous integration#78
xiuliren wants to merge 167 commits into
masterfrom
ci

Conversation

@xiuliren
Copy link
Copy Markdown
Collaborator

  • upgrade python version in ci

xiuliren and others added 30 commits September 28, 2020 08:30
* compiles using cmake; we'll use cmake in setup.py later

* setup.py works

* move CMakeList.txt file to cpp folder

* cmake build output file setup

* test skeleton fixed

* make segmentation a separate module
* output some segmentation with a lot of mergers even with low=0.5

* somehow works, segmentation fault in some run, not stable

* watershed is stable without crashing now. memory issue solved.
* use ptrdiff_t to avoid subtraction bug;

* fixed the watershed bug by using ptrdiff_t for all the volume size.
* agglomeration kind of works

* use size_t for index

* greedy mean affinity agglomeration is working
* initial implementation; the fragments got merged, but is not replected in the final segmentation.

* minor fix; merge two steps;

* works correctly, we only need to use lower min threshold to make the size threshold work

* reorganize code and create a folder called segmentation;
* initial implementation; the fragments got merged, but is not replected in the final segmentation.

* minor fix; merge two steps;

* works correctly, we only need to use lower min threshold to make the size threshold work

* reorganize code and create a folder called segmentation;

* implemented, runs, but nothing changes.

* dilation works, but the segmentation do not look good

* fill background with affinity guidance
… then dilate the segmentation, after that we do aggressive agglomeration.
…onversion from pytensor to tensor is not working due to lvalue and rvalue issue
… neighbors to more neighbors; the segmentation is till not quite good
…erence. The bug might be in the erasion of elements.
…he invalid edge iteration anymore. this looks good, but the result still have many little pieces.
xiuliren added 29 commits July 21, 2021 09:36
* merge the small fragments by finding the maximum edge

* add voxel number threshold parameter to greedy merge function

* we are getting reasonable segmentation
* update test_region_graph

* merge array for disjoint sets; also add unit tests for disjoint sets

* add to_array function for disjoint sets

* use column as segid list, this is more consistent with other formats in machine learning
* add unit test for preprocess; remove object contact is really working

* inplace segmentation of watershed

* seeded watershed

* add robin map github repo as submodule since robin_map is not updated in conda-forge

* make the priority queue more general to use

* update the edit of priority queue

* move priority queue to utils

* move priority queue back to segmentation since the functions are built in for the edge type

* seeded watershed compiles, but runs with core dump error

* compilation in macbook pro

* unit test for seeded watershed. the correctness of the result is not checked

* add segmentation module with 2d seeded watershed

* fixed the bug; the code still has a lot of assertion

* remove a lot of assertions

* test seeded watershed 3d
* rename greedy_merge to greedy_mean_affinity_agglomeration

* get ride of volume boundary flag. we can just use zero-filling and the voxels outside of the volume will have zero segmentation id

* get contacting and inner object ids

* split the region graph arrays to edge array and sum vector

* fix shape assersion bug

* merge arrays for region graph
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants