Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Python crash when I launch unmixing #5

Open
MattiaRigi97 opened this issue Nov 5, 2024 · 0 comments
Open

Python crash when I launch unmixing #5

MattiaRigi97 opened this issue Nov 5, 2024 · 0 comments

Comments

@MattiaRigi97
Copy link

MattiaRigi97 commented Nov 5, 2024

Hi,

I've installed on MacOS with Apple M3 Pro and 18GB of memory:

  • Matlab R2024b
  • Python 3.10.15
  • A virtual env with the requirements for HySUPP

When I launch the example command ! python unmixing.py data=DC2 model=SUnAA SNR=30 python crash. I have tested also with other models and params. Here the output:

! python unmixing.py data=DC2 model=SUnAA SNR=30

05-Nov-24 19:53:02 - main - [DEBUG] - Config:
DATA_dir: ./data/
FIGS_dir: ./figs/
MATLAB_root: /home/clear/azouaoui/code/matlab/
SNR: 30
data:
data_dir: ./data/
dataset: DC2
figs_dir: ./figs/
name: src.data.base.HSIWithGT
extractor:
name: src.model.extractors.VCA
force_align: false
formatters:
simple:
datefmt: '%d-%b-%y %H:%M:%S'
format: '%(asctime)s - %(name)s - [%(levelname)s] - %(message)s'
handlers:
console:
class: logging.StreamHandler
formatter: simple
level: DEBUG
stream: ext://sys.stdout
l2_normalization: false
loggers:
sampleLogger:
handlers:
- console
level: DEBUG
propagate: true
mode: semi
model:
T: 500
low_rank: false
mode: semi
name: src.model.semisupervised.SUnAA
noise:
SNR: 30
name: src.data.noise.AdditiveWhiteGaussianNoise
projection: false
root:
handlers:

  • console
    level: DEBUG
    seed: 0
    version: 1

05-Nov-24 19:53:02 - main - [INFO] - Unmixing mode: SEMI
05-Nov-24 19:53:02 - matplotlib - [DEBUG] - matplotlib data path: /Users/mattiarigiroli/phd-engine/HySUPP/venv/lib/python3.10/site-packages/matplotlib/mpl-data
05-Nov-24 19:53:02 - matplotlib - [DEBUG] - CONFIGDIR=/Users/mattiarigiroli/.matplotlib
05-Nov-24 19:53:02 - matplotlib - [DEBUG] - interactive is False
05-Nov-24 19:53:02 - matplotlib - [DEBUG] - platform is darwin
05-Nov-24 19:53:02 - matplotlib - [DEBUG] - CACHEDIR=/Users/mattiarigiroli/.matplotlib
05-Nov-24 19:53:02 - matplotlib.font_manager - [DEBUG] - Using fontManager instance from /Users/mattiarigiroli/.matplotlib/fontlist-v330.json
05-Nov-24 19:53:02 - src.semisupervised - [INFO] - Semi-Supervised Unmixing - [START]...
05-Nov-24 19:53:02 - src.data.base - [DEBUG] - Path to be opened: ./data/DC2.mat
05-Nov-24 19:53:02 - src.data.base - [DEBUG] - Data keys: dict_keys(['header', 'version', 'globals', 'Y', 'E', 'A', 'D', 'H', 'W', 'p', 'L', 'M', 'N', 'index'])
05-Nov-24 19:53:02 - src.semisupervised - [INFO] - HSI => DC2

224 bands,
100 lines, 100 samples (10000 pixels),
9 endmembers (['#0', '#1', '#2', '#3', '#4', '#5', '#6', '#7', '#8']),
240 atoms
GlobalMinValue: 0.02272115275293592, GlobalMaxValue: 0.9662235319076795

05-Nov-24 19:53:02 - src.data.noise - [DEBUG] - Y shape => (224, 10000)
05-Nov-24 19:53:02 - src.data.noise - [INFO] - Desired SNR => 30
05-Nov-24 19:53:02 - src.data.noise - [DEBUG] - Sigmas after normalization: 0.0668153104781061
05-Nov-24 19:53:02 - src.data.noise - [DEBUG] - Sigma mean based on SNR: 0.3221919872184824
05-Nov-24 19:53:02 - src.data.noise - [DEBUG] - Final sigmas value: 0.021527357659560896
05-Nov-24 19:53:05 - src.model.semisupervised.SUnAA - [INFO] - Initial loss => 78366.76
0%| | 0/500 [00:00<?, ?it/s][1] 19388 segmentation fault python unmixing.py data=DC2 model=SUnAA SNR=30

/usr/local/Cellar/[email protected]/3.10.15/Frameworks/Python.framework/Versions/3.10/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '

Do you have any advice?

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

No branches or pull requests

1 participant