import argparse
import logging
import os
import sys
from functools import partial
import numpy as np
from imsegm.utilities import ImageDimensionError
sys.path += [os.path.abspath('.'), os.path.abspath('..')] # Add path to root
import imsegm.utilities.data_io as tl_data
import imsegm.utilities.experiments as tl_expt
NB_WORKERS = tl_expt.get_nb_workers(0.9)
PATH_IMAGES = tl_data.update_path(
os.path.join('data-images', 'drosophila_ovary_slice'))
PATH_RESULTS = tl_data.update_path('results', absolute=True)
PATHS = {
'annot': os.path.join(PATH_IMAGES, 'annot_eggs', '*.png'),
'image': os.path.join(PATH_IMAGES, 'image', '*.jpg'),
'output': os.path.join(PATH_RESULTS, 'cut_images'),
}
def arg_parse_params(dict_paths):
"""
SEE: https://docs.python.org/3/library/argparse.html
:return ({str: str}, int):
"""
from imsegm.superpixels import segment_slic_img2d, segment_slic_img3d_gray
from imsegm.utilities import ImageDimensionError
from imsegm.utilities.experiments import get_nb_workers, WrapExecuteSequence
# from sklearn import mixture
#: select basic features extracted from superpixels
FTS_SET_SIMPLE = FEATURES_SET_COLOR
#: select default Classifier for supervised segmentation
CLASSIF_NAME = DEFAULT_CLASSIF_NAME
#: select default Modeling/clustering for unsupervised segmentation
CLUSTER_METHOD = DEFAULT_CLUSTERING
#: define how many images will be left out during cross-validation training
CROSS_VAL_LEAVE_OUT = 2
#: default number of workers
NB_WORKERS = get_nb_workers(0.6)
def pipe_color2d_slic_features_model_graphcut(
image,
nb_classes,
dict_features,
sp_size=30,
sp_regul=0.2,
pca_coef=None,
use_scaler=True,
estim_model='GMM',
gc_regul=1.,
gc_edge_type='model',
debug_visual=None,
):
