def test_egl_and_osmesa_sawp_and_equivalence():
from syconn import global_params
global_params.config['pyopengl_platform'] = 'egl'
from syconn.proc.ssd_assembly import init_sso_from_kzip
from syconn.proc.rendering import render_sso_coords, \
render_sso_coords_index_views
import os
import numpy as np
fname = os.path.dirname(__file__) + '/renderexample.k.zip'
assert os.path.isfile(fname)
ssv = init_sso_from_kzip(fname, sso_id=1)
rendering_locations = np.concatenate(ssv.sample_locations())
index_views = render_sso_coords_index_views(ssv,
rendering_locations,
verbose=True)
raw_views = render_sso_coords(ssv, rendering_locations, verbose=True)
global_params.config['pyopengl_platform'] = 'osmesa'
index_views_osmesa = render_sso_coords_index_views(ssv,
rendering_locations,
verbose=True)
raw_views_osmesa = render_sso_coords(ssv,
rendering_locations,
verbose=True)
nb_of_pixels = np.prod(raw_views.shape)
# fraction of different vertex indices must be below 1 out of 100k
assert np.sum(index_views != index_views_osmesa) / nb_of_pixels < 1e-5
# maximum deviation of depth value must be smaller
assert np.max(((raw_views - raw_views_osmesa)**2)**0.5) == 1
# affected pixels must be below 0.05
assert np.sum(raw_views != raw_views_osmesa) / nb_of_pixels < 0.05
def test_raw_and_index_rendering_egl():
from syconn import global_params
global_params.config['pyopengl_platform'] = 'egl'
from syconn.proc.ssd_assembly import init_sso_from_kzip
from syconn.proc.rendering import render_sso_coords, \
render_sso_coords_index_views
import os
import numpy as np
fname = os.path.dirname(__file__) + '/renderexample.k.zip'
assert os.path.isfile(fname)
ssv = init_sso_from_kzip(fname, sso_id=1)
rendering_locations = np.concatenate(ssv.sample_locations())
index_views = render_sso_coords_index_views(ssv,
rendering_locations,
verbose=True)
raw_views = render_sso_coords(ssv, rendering_locations, verbose=True)
assert len(index_views) == len(raw_views)
# path to working directory of example cube - required to load pretrained models
path_to_workingdir = os.path.expanduser(args.working_dir)
# path to cell reconstruction k.zip
cell_kzip_fn = os.path.abspath(os.path.expanduser(args.kzip))
if not os.path.isfile(cell_kzip_fn):
raise FileNotFoundError
# set working directory to obtain models
global_params.wd = path_to_workingdir
# get model for spine detection
m = get_semseg_spiness_model()
# load SSO instance from k.zip file
sso = init_sso_from_kzip(cell_kzip_fn, sso_id=1)
# run prediction and store result in new kzip
cell_kzip_fn_spines = cell_kzip_fn[:-6] + '_spines.k.zip'
semseg_of_sso_nocache(sso,
dest_path=cell_kzip_fn_spines,
verbose=True,
semseg_key="spinesstest",
k=0,
ws=(256, 128),
model=m,
nb_views=2,
comp_window=8e3)
node_preds = sso.semseg_for_coords(sso.skeleton['nodes'], "spinesstest",
**global_params.semseg2coords_spines)
sso.skeleton["spinesstest"] = node_preds
help='path to kzip file which contains a cell reconstruction (see '
'SuperSegmentationObject().export2kzip())')
args = parser.parse_args()
# path to working directory of example cube - required to load pretrained models
path_to_workingdir = os.path.expanduser(args.working_dir)
# path to cell reconstruction k.zip
cell_kzip_fn = os.path.expanduser(args.kzip)
# set working directory to obtain models
global_params.wd = path_to_workingdir
# get model for spine detection
m = get_semseg_spiness_model()
# load SSO instance from k.zip file
sso = init_sso_from_kzip(cell_kzip_fn)
# run prediction and store result in new kzip
cell_kzip_fn_spines = cell_kzip_fn[:-6] + '_spines.k.zip'
semseg_of_sso_nocache(sso,
dest_path=cell_kzip_fn_spines,
semseg_key="spinesstest",
n_avg=5,
ws=(256, 128),
model=m,
nb_views=2,
comp_window=8e3,
verbose=True)