def test_watershed_seeded():
seeds_bool = (landscape == 0)
seeds_unique = nd.label(seeds_bool)[0]
seeded_watershed_result = np.array([1,1,1,1,1,0,2,2,2,0,3,3])
seeded_watershed1 = morpho.watershed(landscape, seeds_bool, dams=True)
seeded_watershed2 = morpho.watershed(landscape, seeds_unique, dams=True)
assert_array_equal(seeded_watershed1, seeded_watershed_result)
assert_array_equal(seeded_watershed2, seeded_watershed_result)
def test_watershed_seeded():
seeds_bool = (landscape == 0)
seeds_unique = nd.label(seeds_bool)[0]
seeded_watershed_result = np.array([1,1,1,1,1,0,2,2,2,0,3,3])
seeded_watershed1 = morpho.watershed(landscape, seeds_bool, dams=True)
seeded_watershed2 = morpho.watershed(landscape, seeds_unique, dams=True)
assert_array_equal(seeded_watershed1, seeded_watershed_result)
assert_array_equal(seeded_watershed2, seeded_watershed_result)
def main(args):
ws_id = generate_ws_id(args.min_seed_size, args.connectivity,
args.smooth_thresh, args.keep_speckles, args.override_skimage)
paths = get_paths("XX", args.traintest, args.size, args.volume_id,
"idsia", "XX", "XX", "XX", ws_id)
stack = read_h5(paths["hypercubes"], args.h5_key)
if args.dry_run: stack = stack[:2,:,:]
if not args.dont_invert: stack[...] = invert_gray(stack)
ws = np.zeros(stack.shape)
cur_max = 0
for ii in range(stack.shape[0]):
print ii
ws[ii,:,:] = morpho.watershed(stack[ii,:,:], minimum_seed_size=args.min_seed_size,
connectivity=args.connectivity, smooth_thresh=args.smooth_thresh,
override_skimage=args.override_skimage) + cur_max
cur_max = ws[ii,:,:].max()
ws = ws.astype('int64')
print "unique labels in ws:",np.unique(ws).size
if not args.keep_speckles:
ws = agglo.despeckle_watershed(ws)
print "unique labels after despeckling:",np.unique(ws).size
ws, _, _ = evaluate.relabel_from_one(ws)
if ws.min() < 1: ws += (1-ws.min())
write_h5(ws, paths["watersheds"], dry=args.dry_run)
if args.no_quarters or (args.size != "whole"): return
for row_start, row_end, col_start, col_end, frame_start, frame_end, label, size in fractions:
path = generate_path(args.traintest, size, label, ws_id)
write_h5(ws[frame_start:frame_end, row_start:row_end, col_start:col_end], path)
def test_watershed_saddle_basin():
saddle_landscape = np.array([[0,0,3],[2,1,2],[0,0,3]])
saddle_result = np.array([[1,1,1],[0,0,0],[2,2,2]])
saddle_ws = morpho.watershed(saddle_landscape, dams=True)
assert_array_equal(saddle_ws, saddle_result)
def test_watershed_seeded_nodams():
seeds_bool = landscape==0
seeded_nodam_ws_result = np.array([1,1,1,1,1,1,2,2,2,3,3,3])
seeded_nodam_ws = morpho.watershed(landscape,
seeds=seeds_bool, override_skimage=True, dams=False)
assert_array_equal(seeded_nodam_ws, seeded_nodam_ws_result)
def test_watershed_nodams():
nodam_watershed_result = np.array([1,1,1,2,2,2,3,3,3,4,4,4])
nodam_watershed = morpho.watershed(landscape, dams=False)
assert_array_equal(nodam_watershed, nodam_watershed_result)
def test_watershed():
regular_watershed_result = np.array([1,1,1,0,2,0,3,3,3,0,4,4])
regular_watershed = morpho.watershed(landscape, dams=True)
assert_array_equal(regular_watershed, regular_watershed_result)
def test_watershed_images():
wss = [morpho.watershed(probs[i], dams=True) for i in range(3)] + \
[morpho.watershed(probs[3], dams=False)]
for i, (ws, res) in enumerate(zip(wss, results)):
assert_array_equal(ws, res, 'Image watershed test %i failed.' % i)
def test_watershed_saddle_basin():
saddle_landscape = np.array([[0,0,3],[2,1,2],[0,0,3]])
saddle_result = np.array([[1,1,1],[0,0,0],[2,2,2]])
saddle_ws = morpho.watershed(saddle_landscape, dams=True)
assert_array_equal(saddle_ws, saddle_result)
def test_watershed_seeded_nodams():
seeds_bool = landscape==0
seeded_nodam_ws_result = np.array([1,1,1,1,1,1,2,2,2,3,3,3])
seeded_nodam_ws = morpho.watershed(landscape,
seeds=seeds_bool, override_skimage=True, dams=False)
assert_array_equal(seeded_nodam_ws, seeded_nodam_ws_result)
def test_watershed_nodams():
nodam_watershed_result = np.array([1,1,1,2,2,2,3,3,3,4,4,4])
nodam_watershed = morpho.watershed(landscape, dams=False)
assert_array_equal(nodam_watershed, nodam_watershed_result)
def test_watershed():
regular_watershed_result = np.array([1,1,1,0,2,0,3,3,3,0,4,4])
regular_watershed = morpho.watershed(landscape, dams=True)
assert_array_equal(regular_watershed, regular_watershed_result)
def test_watershed_images():
wss = [morpho.watershed(probs[i], dams=(i == 0)) for i in range(2)]
for i, (ws, res) in enumerate(zip(wss, results)):
yield (assert_array_equal, ws, res,
'Image watershed test %i failed.' % i)
# Do watershed
min_seed_size = 2
connectivity = 2
smooth_thresh = 0.02
override = 0
#membraneTrain = membraneTrain.astype('float64')/255.0
ws_train = np.zeros(membraneTrain.shape)
cur_max = 0
for ii in range(membraneTrain.shape[0]):
print ii
ws_train[ii, :, :] = morpho.watershed(
1 - membraneTrain[ii, :, :],
connectivity=connectivity,
smooth_thresh=smooth_thresh,
override_skimage=override,
minimum_seed_size=min_seed_size) + cur_max
cur_max = ws_train[ii, :, :].max()
ws_train = ws_train.astype('int64')
print "unique labels in ws:", np.unique(ws_train).size
ws_train = optimized.despeckle_watershed(ws_train)
print "unique labels after despeckling:", np.unique(ws_train).size
ws_train, _, _ = evaluate.relabel_from_one(ws_train)
if ws_train.min() < 1:
ws_train += (1 - ws_train.min())
from skimage.morphology import closing
from skimage.morphology import binary_dilation
from skimage.morphology import binary_erosion
from skimage.filters.rank import threshold
import matplotlib.pyplot as plt
# Gather images from nXp_data.npy file
print "Getting images"
membrane_images = np.load('nXp_data.npy')
pre_image = 255 * membrane_images[0]
min_seed_size = 5 #2
connectivity = 2 #2
smooth_thresh = 0.02 #0.02
ws_train = morpho.watershed(pre_image,
connectivity=connectivity, smooth_thresh=smooth_thresh,
override_skimage=1,minimum_seed_size=min_seed_size) + 1
#ws_train = ws_train
fig, axes = plt.subplots(ncols=1, figsize=(8, 2.7), sharex=True, sharey=True, subplot_kw={'adjustable':'box-forced'})
ax0 = axes
ax0.imshow(ws_train)#, cmap=plt.cm.spectral, interpolation='nearest')
ax0.set_title('Overlapping objects')
fig.subplots_adjust(hspace=0.01, wspace=0.01, top=0.9, bottom=0, left=0,
right=1)
plt.show()
