delta.config

Click on the signatures below to get a complete description.

Module for configuration files and configuration parameters

@author: jblugagne

Module Attributes

presets	Type of analysis: can be '2D', 'mothermachine', or your own custom name for presets
models	Which models will be run
model_file_rois	Model file for ROIs segmentation
model_file_seg	Model file for cell segmentation
model_file_track	Model file for cell tracking
target_size_rois	ROI U-Net target/input image size
target_size_seg	segmentation U-Net target/input image size
target_size_track	tracking U-Net target/input image size
training_set_rois	Path to ROIs U-Net training set
training_set_seg	Path to segmentation training set
training_set_track	Path to tracking training set
eval_movie	Path to evaluation movie / image sequence
rotation_correction	Flag to try to automatically correct image rotation (for microfluidic devices)
drift_correction	Flag to correct drift over time (for microfluidic devices / ROIs)
crop_windows	Flag to crop input image into windows of size target_size_seg for segmentation, otherwise resize them
min_roi_area	Minimum area of detected ROIs, in pixels.
whole_frame_drift	If correcting for drift, use the entire frame instead of the region above the chambers
min_cell_area	Minimum area of detected cells, in pixels.
save_format	Format to save output data to
TF_CPP_MIN_LOG_LEVEL	Debugging messages level from Tensorflow ('0' = most verbose to '3' = not verbose)
memory_growth_limit	If running into OOM issues or having trouble with cuDNN loading, try setting memory_growth_limit to a value in MB: (eg 1024, 2048...)
pipeline_seg_batch	If running into OOM issues during segmentation with the pipeline, try lowering this value.
pipeline_track_batch	If running into OOM issues during tracking with the pipeline, try lowering this value.

Functions

load_config([json_file, presets, config_level])

Loads json configuration files