Open source Python library for building bioimage analysis pipelines
MIT License
Published by danifranco 9 months ago
Quick patch to fix some issues:
sys.exit()
call to main.py
to prevent errors inside jupyter notebooksDATA.PREPROCESSING.*.ACTIVATE
to ENABLE
as in other variables.DATA.PREPROCESS.MEDIAN_BLUR.FOOTPRINT
as it is a Numpy array and it can not be declared through YACSPublished by danifranco 9 months ago
Quick patch to fix some issues:
FORCE_RGB
variable usage in classificationrelabel_sequential()
to be as the old function we were using so the matching metrics process doesn't get stuck anymore.Published by danifranco 9 months ago
TEST.POST_PROCESSING.MEASURE_PROPERTIES
and TEST.POST_PROCESSING.MEASURE_PROPERTIES.REMOVE_BY_PROPERTIES
TEST.DET_EXCLUDE_BORDER
optionMODEL.N_CLASSES
solvedTEST.BY_CHUNKS
selected using TEST.BY_CHUNKS.INPUT_IMG_AXES_ORDER
of len 4.Published by danifranco 10 months ago
TEST.BY_CHUNKS.INPUT_IMG_AXES_ORDER
to control the order of the Zarr/H5 input image axesPROBLEM.INSTANCE_SEG.DATA_CHECK_MW
to False
PROBLEM.DETECTION.DATA_CHECK_MW
to False
DATA.VAL.SPLIT_TRAIN
to 0.1
TEST.MATCHING_SEGCOMPARE
not usedTEST.BY_CHUNKS
settingTEST.BY_CHUNKS
when no GPU is usedPublished by danifranco 12 months ago
New functionality added:
TEST.POST_PROCESSING.REMOVE_BY_PROPERTIES
, and its options, to remove instances by the conditions based in each instance properties. This merges PROBLEM.INSTANCE_SEG.WATERSHED_CIRCULARITY
, PROBLEM.INSTANCE_SEG.DATA_REMOVE_SMALL_OBJ_AFTER
and PROBLEM.INSTANCE_SEG.DATA_REMOVE_SMALL_OBJ_AFTER
functionalities.load_sample
function inside the generators if DATA.*.IN_MEMORY
is selected, which allows to have in memory the dataset in its original dtype (usuarlly uint8
or uint16
) and not in float32
, consuming less memory, at the cost of having to do the normalization per batch.TEST.REDUCE_MEMORY
option to reduce also the dtype of the prediction from float32
to float16
TEST.BY_CHUNKS
, and its options, to process large images by chunks: load/save steps work with H5
or Zarr
formats. This option helps to generate model's prediction with overlap/padding with low memory footprint by constructing it patch by patch. It is also prepared to do multi-GPU inference to accelerate the reconstruction process. It can also work loading TIF
images but with H5
and Zarr
only the patches processed are loaded into memory, and nothing else, so you can should scale to TB of data without having memory problems.TEST.BY_CHUNKS.WORKFLOW_PROCESS
, and a few more options related to it, to continue or not the workflow normal steps after the model prediction. With TEST.BY_CHUNKS.WORKFLOW_PROCESS.TYPE
you can tell the worklow to process the predicted image patch by patch or as just one image. By patch option is currently only supported in DETECTION
workflow.MODEL.KERNEL_INIT
TRAIN.PATIENCE
default changed to -1
utils/scripts/h5_to_zarr.py
auxiliary scriptwarmupcosine
learning rate scheduler is done by iterations and not by epochs.TEST.POST_PROCESSING.CLEAR_BORDER
to remove instances in the borderTEST.DET_LOCAL_MAX_COORDS
optionTEST.DET_POINT_CREATION_FUNCTION
, and a few more options related to it, to decide whether to use peak_local_max
or blob_log
(from scikit-image) functions to create the final points from probabilities.MODEL.MAE_MASK_RATIO
option3D
supportPublished by danifranco about 1 year ago
Major changes:
@inproceedings{franco2023biapy,
title={BiaPy: a ready-to-use library for Bioimage Analysis Pipelines},
author={Franco-Barranco, Daniel and Andr{\'e}s-San Rom{\'a}n, Jes{\'u}s A and G{\'o}mez-G{\'a}lvez, Pedro and Escudero, Luis M and Mu{\~n}oz-Barrutia, Arrate and Arganda-Carreras, Ignacio},
booktitle={2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)},
pages={1--5},
year={2023},
organization={IEEE}
}
Published by danifranco about 3 years ago
This version of the project should be used to reproduce all the results reported in the following work:
@misc{francobarranco2021stable,
title={Stable deep neural network architectures for mitochondria segmentation on electron microscopy volumes},
author={Daniel Franco-Barranco and Arrate Muñoz-Barrutia and Ignacio Arganda-Carreras},
year={2021},
eprint={2104.03577},
archivePrefix={arXiv},
primaryClass={eess.IV}
}
For here on we will move to newest versions of Tensorflow/Keras and some parts of the code could change.
Published by danifranco about 3 years ago
Major changes: