Skip to content

Add scripts and files to process Vi's screen#14

Open
jni wants to merge 26 commits into
microscopium:masterfrom
jni:vi
Open

Add scripts and files to process Vi's screen#14
jni wants to merge 26 commits into
microscopium:masterfrom
jni:vi

Conversation

@jni

@jni jni commented Nov 19, 2018

Copy link
Copy Markdown
Contributor

Uses dask-jobqueue for the main workflow.

@jni

jni commented Nov 19, 2018

Copy link
Copy Markdown
Contributor Author

@GenevieveBuckley please annotate the bits of code that need clarification and I'll add comments, as I think these scripts should be used as templates to generalise to new screens, so they should be well documented.

Comment thread jobqueue.yaml Outdated
Comment thread slurm-convert-tifs.sh
Comment thread slurm.sh
# SBATCH --mail-user=juan.nunez-iglesias@monash.edu
# SBATCH --mail-type=END
# SBATCH --mail-type=FAIL
/home/jnun0003/.conda/envs/mic/bin/python ./single-process-vi.py

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same again, scripts in shared spaces would be better.

Comment thread vi-start-to-finish.py
Comment thread vi-start-to-finish.py Outdated
Comment thread vi-start-to-finish.py Outdated
Comment thread vi-start-to-finish.py
Comment thread vi-start-to-finish.py
@jni

jni commented Nov 19, 2018

Copy link
Copy Markdown
Contributor Author

I forgot to include the output, which made me very happy (after seeing many outputs with full tracebacks and half-finished progress bars =P):

In [1]: %run -i vi-start-to-finish.py
illum: 100%|████████████████████████████████████████████████████████████████████████████████| 284/284 [42:31<00:00,  8.99s/it]
illumination estimated in 42.0m31.0s
illum-corr: 100%|████████████████████████████████████████████████████████████████████████| 284/284 [2:51:22<00:00, 172.00s/it]
illumination corrected in 2.0h51.0m22.0s
montage: 100%|██████████████████████████████████████████████████████████████████████████| 54528/54528 [44:46<00:00,  7.50it/s]
montaged in 46.0m8.0s
features:  50%|██████████████████████████████████▍                                  | 27183/54528 [1:02:34<1:02:27,  7.30it/s]distributed.scheduler - ERROR - Workers don't have promised key: ['tcp://172.16.193.188:41686'], features-55f478c8aca9dcbd97f98cdeb1d49b36
NoneType: None
distributed.client - WARNING - Couldn't gather 1 keys, rescheduling {'features-55f478c8aca9dcbd97f98cdeb1d49b36': ('tcp://172.16.193.188:41686',)}
features:  99%|██████████████████████████████████████████████████████████████████████▎| 54046/54528 [2:04:04<01:36,  4.99it/s]distributed.scheduler - ERROR - Workers don't have promised key: ['tcp://172.16.193.190:39647'], features-15f2d90c870cd1ef0dc775bbf90374d1
NoneType: None
distributed.client - WARNING - Couldn't gather 1 keys, rescheduling {'features-15f2d90c870cd1ef0dc775bbf90374d1': ('tcp://172.16.193.190:39647',)}
features: 100%|███████████████████████████████████████████████████████████████████████| 54528/54528 [2:05:46<00:00,  7.23it/s]
features computed in 2.0h6.0m22.0s

Needless to say I don't know yet what those "Workers don't have promised key", but it doesn't seem to have affected any feature computation.

@GenevieveBuckley

Copy link
Copy Markdown

I think now that UMAP is being included more routinely in these scripts (eg: c236e06) we should update requirements.txt and environment.yml in the microscopium repo. Thoughts?

@jni

jni commented Nov 26, 2018

Copy link
Copy Markdown
Contributor Author

Hmm, I thought I'd responded to this, sorry, my bad! Thoughts: when we pull these things into microscopium proper, we can update the requirements. As we've discussed recently, one thing I want to do pretty short term is to go from images + info-csv + config file to the full feature computation and dimensionality reduction. That PR is the place to update the requirements.

@jni

jni commented Nov 26, 2018

Copy link
Copy Markdown
Contributor Author

btw assuming you have no further questions I think this is ready to merge.

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