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)
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())
ws_train = ws_train.astype('int64')
print "Training watershed complete"
print "Watershed train (VI, ARI)"
vi_ws_train = ev.split_vi(ws_train, gt_train),
ari_ws_train = ev.adj_rand_index(ws_train, gt_train)
print vi_ws_train
print ari_ws_train
scipy.io.savemat('trainWS.mat', mdict={'ws_train': ws_train})
scipy.io.savemat('trainMembrane.mat', mdict={'membraneTrain': membraneTrain})
# create graph and obtain a training dataset
if algo == 1: #run gala
fc = features.base.Composite(children=[features.moments.Manager(), features.histogram.Manager(25, 0, 1, [0.1, 0.5, 0.9]),
features.graph.Manager(), features.contact.Manager([0.1, 0.5, 0.9]) ])
rf = classify.load_classifier(sys.argv[6])
learned_policy = agglo.classifier_probability(fc, rf)
print 'applying classifier...'
g_test = agglo.Rag(ws, membrane, learned_policy, feature_manager=fc)
print 'choosing best operating point...'
g_test.agglomerate(thresh) # best expected segmentation
cube = g_test.get_segmentation()
cube, _, _ = evaluate.relabel_from_one(cube)
print "Completed Gala Run"
# gala allows implementation of other agglomerative algorithms, including
# the default, mean agglomeration
if algo == 2: #mean agglomeration
print 'mean agglomeration step...'
g_testm = agglo.Rag(ws, membrane, merge_priority_function=agglo.boundary_mean)
g_testm.agglomerate(thresh)
cube = g_testm.get_segmentation()
cube, _, _ = evaluate.relabel_from_one(cube)
print "Completed Mean Agglo"
fc = features.base.Composite(children=[
features.moments.Manager(),
features.histogram.Manager(25, 0, 1, [0.1, 0.5, 0.9]),
features.graph.Manager(),
features.contact.Manager([0.1, 0.5, 0.9])
])
rf = classify.load_classifier(sys.argv[6])
learned_policy = agglo.classifier_probability(fc, rf)
print 'applying classifier...'
g_test = agglo.Rag(ws, membrane, learned_policy, feature_manager=fc)
print 'choosing best operating point...'
g_test.agglomerate(thresh) # best expected segmentation
cube = g_test.get_segmentation()
cube, _, _ = evaluate.relabel_from_one(cube)
print "Completed Gala Run"
# gala allows implementation of other agglomerative algorithms, including
# the default, mean agglomeration
if algo == 2: #mean agglomeration
print 'mean agglomeration step...'
g_testm = agglo.Rag(ws,
membrane,
merge_priority_function=agglo.boundary_mean)
g_testm.agglomerate(thresh)
cube = g_testm.get_segmentation()
cube, _, _ = evaluate.relabel_from_one(cube)
ws_test=np.zeros(membraneTest.shape)
cur_max = 0
for ii in range(membraneTest.shape[0]):
print ii
ws_test[ii,:,:] = morpho.watershed(membraneTest[ii,:,:],
connectivity=connectivity, smooth_thresh=smooth_thresh,
override_skimage=override,minimum_seed_size=min_seed_size) + cur_max
cur_max = ws_test[ii,:,:].max()
print ws_test.dtype
ws_test = ws_test.astype('int64')
print "unique labels in ws:",np.unique(ws_test).size
ws_test = optimized.despeckle_watershed(ws_test)
print "unique labels after despeckling:",np.unique(ws_test).size
ws_test, _, _ = evaluate.relabel_from_one(ws_test)
if ws_test.min() < 1:
ws_test += (1-ws_test.min())
print "Testing watershed complete"
print "Watershed test (VI, ARI)"
vi_ws_test = ev.split_vi(ws_test, gt_test),
ari_ws_test = ev.adj_rand_index(ws_test, gt_test)
print vi_ws_test
print ari_ws_test
scipy.io.savemat('testWS.mat', mdict={'ws_test':ws_test})
print 'Time Elapsed So Far: ' + str(time.time()-start)
