def test_contingency_table():
seg = np.array([0, 1, 1, 1, 2, 2, 2, 3])
gt = np.array([1, 1, 1, 2, 2, 2, 2, 0])
ct = ev.contingency_table(seg, gt, ignore_seg=[], ignore_gt=[])
ct0 = ev.contingency_table(seg, gt, ignore_seg=[0], ignore_gt=[0])
ctd = ct.todense()
assert_equal(
ctd,
np.array([[0., 0.125, 0.], [0., 0.25, 0.125], [0., 0., 0.375],
[0.125, 0., 0.]]))
assert ct.shape == ct0.shape
def test_contingency_table():
seg = np.array([0, 1, 1, 1, 2, 2, 2, 3])
gt = np.array([1, 1, 1, 2, 2, 2, 2, 0])
ct = ev.contingency_table(seg, gt, ignore_seg=[], ignore_gt=[])
ct0 = ev.contingency_table(seg, gt, ignore_seg=[0], ignore_gt=[0])
ctd = ct.todense()
assert_equal(ctd, np.array([[0. , 0.125, 0. ],
[0. , 0.25 , 0.125],
[0. , 0. , 0.375],
[0.125, 0. , 0. ]]))
assert ct.shape == ct0.shape
def show_greatest_vi(seg, gt):
(worst_false_merges, merge_ents, worst_false_splits, split_ents) = evaluate.sorted_vi_components(seg, gt)
print "Total entropy of false merges: %f" % sum(merge_ents)
print "Total entropy of false splits: %f" % sum(split_ents)
worst_false_splits = worst_false_splits[:LIST_CAP]
split_ents = split_ents[:LIST_CAP]
worst_false_merges = worst_false_merges[:LIST_CAP]
merge_ents = merge_ents[:LIST_CAP]
# for label, entropies in [("merges", merge_ents), ("splits", split_ents)]:
# print "For worst false %s, top %d biggest entropies:" % (label, len(entropies))
# for rank, entropy in enumerate(entropies):
# print " %d. %f" % (rank, entropy)
# handle worst false splits
print worst_false_splits
cont_table = evaluate.contingency_table(seg, gt)
# view_biggest_cross_section(gt, [worst_false_splits[0]])
# for bad_merge_id_in_seg in worst_false_merges[1:3]:
# overlaps = evaluate.split_components(bad_merge_id_in_seg, cont_table, axis=0)
# print "bad_merge_id_in_seg:",bad_merge_id_in_seg
# print overlaps
# overlap_ids = [gt_id for gt_id, perc_of_bad_split, perc_in_bad_split in overlaps]
# view_bad_merge(seg, gt, bad_merge_id_in_seg, overlap_ids)
for bad_split_id_in_gt in worst_false_splits[:1]:
overlaps = evaluate.split_components(bad_split_id_in_gt, cont_table, axis=1)
print "bad_split_id_in_gt:", bad_split_id_in_gt
print overlaps
overlap_ids = [seg_id for seg_id, perc_of_bad_split, perc_in_bad_split in overlaps]
view_bad_split(seg, gt, bad_split_id_in_gt, overlap_ids)
def view_all_join(gt, automated_seg, num_elem=6, axis=None):
"""Generate an interactive figure highlighting the VI error.
Parameters
----------
gt: nd-array with shape M*N.
This corresponds to the 'ground truth'.
auto: nd-array with same shape as gt. This
corresponds to the automated segmentation.
num_elem: Int, optional.
This parameter determines the number of comps
shown upon click. Set to output '4' by default.
Returns
-------
A window with six panels - the top middle image corresponds to the
components that are the worst false merges in the automated
segmentation, which share significant area with the clicked-upon segment.
Likewise, the top middle image shows the worst false splits.
"""
if gt.shape != automated_seg.shape:
return "Input arrays are not of the same shape."
elif (type(gt) or type(automated_seg)) != np.ndarray:
return "Input arrays not of valid type."
vint = np.vectorize(int)
# Compute the join seg of the automatic seg and the ground truth.
joint_seg = join_segmentations(automated_seg, gt)
# Contingency table for merges
cont_table_m = ev.contingency_table(automated_seg, joint_seg)
# Contingency table for splits
cont_table_s = ev.contingency_table(joint_seg, gt)
# Sort the VI according to the largest false merge components.
merge_idxs_m, merge_errs_m = ev.sorted_vi_components(
joint_seg, automated_seg)[0:2] #merges
#Sort the VI according to the largest false split components.
split_idxs_s, split_errs_s = ev.sorted_vi_components(joint_seg,
gt)[0:2] #split
#Find the indices of these largest false merge components, and largest false splits, in descending order.
merge_idxs_sorted, split_idxs_sorted = np.argsort(
merge_idxs_m), np.argsort(split_idxs_s)
#Sort the errors according to the indices.
merge_unsorted, split_unsorted = merge_errs_m[
merge_idxs_sorted], split_errs_s[split_idxs_sorted]
# Color both the seg and gt according to the intensity of the split VI error.
merge_err_img, split_err_img = merge_unsorted[
automated_seg], split_unsorted[gt]
if axis is None:
fig, ax = plt.subplots(nrows=2, ncols=3, sharex=True, sharey=True)
plt.setp(ax.flat, adjustable='box-forced')
else:
fig, ax = plt.subplots(nrows=len(axis) // 2,
ncols=len(axis) // 2,
sharex=True,
sharey=True)
for i in range(len(axis) // 2):
ax[0, i] = ax[i]
for i in range(0, (len(axis) // 2)):
ax[1, i] = ax[i + 2]
ax[0, 0].imshow(RAW)
viz.imshow_magma(merge_err_img, alpha=0.4, axis=ax[0, 0])
ax[0, 1].imshow(RAW)
axes_image_1 = viz.imshow_rand(joint_seg, alpha=0.4, axis=ax[0, 1])
ax[0, 2].imshow(RAW)
viz.imshow_rand(gt, alpha=0.4, axis=ax[0, 2])
ax[1, 0].imshow(RAW)
viz.imshow_magma(split_err_img, alpha=0.4, axis=ax[1, 0])
ax[1, 1].imshow(RAW)
axes_image = viz.imshow_rand(joint_seg, alpha=0.4, axis=ax[1, 1])
ax[1, 2].imshow(RAW)
viz.imshow_rand(automated_seg, alpha=0.4, axis=ax[1, 2])
ax[0, 0].set_title(
"Worst merge comps colored by VI error: click to show them on second panel."
)
ax[0, 1].set_title("Worst merge comps.")
ax[0, 2].set_title("Ground Truth.")
ax[1, 0].set_title(
"Worst split comps colored by VI error: click to show them on second panel."
)
ax[1, 1].set_title("Worst split comps.")
ax[1, 2].set_title("Automated Seg.")
@jit
def drawer(seg, comps, limit=True):
"""Dynamically redraw the worst split/merge comps."""
a_seg = np.zeros_like(seg.astype('float64'))
factor = (seg.max() // num_elem)
lim = 0.0
for i, (j, k, z) in enumerate(comps):
lim += k
if z < 0.01:
continue
a_seg += (seg == j) * ((i + 1) * factor)
if limit:
if lim >= 0.98:
break
return a_seg
@jit
def _onpress(event):
"""Matplotlib 'onpress' event handler."""
if not (event.inaxes == ax[1, 0] or event.inaxes == ax[0, 0]
or event.inaxes == ax[0, 2] or event.inaxes == ax[1, 2]):
fig.text(0.5,
0.5,
s="Must click on left or right axes to show comps!",
ha="center")
fig.canvas.draw_idle()
if event.inaxes == ax[0, 0] or event.inaxes == ax[0, 2]:
if event.button != 1:
return
for txt in fig.texts:
txt.set_visible(False)
fig.canvas.draw()
x, y = vint(event.xdata), vint(event.ydata)
# Find the indices of the false merge bodies overlapping with the coordinates of the mouse click.
worst_merge_comps_m = ev.split_components(automated_seg[y, x],
num_elems=None,
cont=cont_table_m,
axis=0)
new_seg_m = drawer(joint_seg, worst_merge_comps_m, limit=False)
axes_image_1.set_array(new_seg_m)
fig.canvas.draw()
if event.inaxes == ax[1, 0] or event.inaxes == ax[1, 2]:
if event.button != 1:
return
for txt in fig.texts:
txt.set_visible(False)
fig.canvas.draw()
x, y = vint(event.xdata), vint(event.ydata)
# Find the indices of the false split bodies overlapping with the coordinates of the mouse click.
worst_split_comps_s = ev.split_components(gt[y, x],
num_elems=None,
cont=cont_table_s,
axis=1)
new_seg_s = drawer(joint_seg, worst_split_comps_s)
axes_image.set_array(new_seg_s)
fig.canvas.draw()
fig.canvas.mpl_connect('button_press_event', _onpress)
plt.ioff()
plt.show()
def view_all(gt, automated_seg, num_elem=6, axis=None):
"""Generate an interactive figure highlighting the VI error.
Parameters
----------
gt: nd-array with shape M*N.
This corresponds to the 'ground truth'.
auto: nd-array with same shape as gt. This
corresponds to the automated segmentation.
num_elem: Int, optional.
This parameter determines the number of comps
shown upon click. Set to output '6' by default.
Returns
-------
A panel with six images - the top middle image corresponds to the
components that are the worst false merges in the automated
segmentation, which share significant area with the clicked-upon segment.
Likewise, the top middle image shows the worst false splits.
"""
if gt.shape != automated_seg.shape:
return "Input arrays are not of the same shape."
elif (type(gt) or type(automated_seg)) != np.ndarray:
return "Input arrays not of valid type."
vint = np.vectorize(int)
cont = ev.contingency_table(automated_seg, gt)
ii1, err1, ii2, err2 = ev.sorted_vi_components(automated_seg, gt)
idxs1, idxs2 = np.argsort(ii1), np.argsort(ii2)
err_unsorted, err_unsorted_2 = err1[idxs1], err2[idxs2]
err_img, err_img_1 = err_unsorted[gt], err_unsorted_2[automated_seg]
if axis is None:
fig, ax = plt.subplots(nrows=2, ncols=3, sharex=True, sharey=True)
plt.setp(ax.flat, adjustable='box-forced')
else:
fig, ax = plt.subplots(nrows=len(axis) // 2,
ncols=len(axis) // 2,
sharex=True,
sharey=True)
for i in range(len(axis) // 2):
ax[0, i] = ax[i]
for i in range(0, (len(axis) // 2)):
ax[1, i] = ax[i + 2]
ax[0, 0].imshow(RAW)
viz.imshow_magma(err_img_1, alpha=0.4, axis=ax[0, 0])
ax[0, 1].imshow(RAW)
axes_image_1 = viz.imshow_rand(automated_seg, alpha=0.4, axis=ax[0, 1])
ax[0, 2].imshow(RAW)
viz.imshow_rand(gt, alpha=0.4, axis=ax[0, 2])
ax[1, 0].imshow(RAW)
viz.imshow_magma(err_img, alpha=0.4, axis=ax[1, 0])
ax[1, 1].imshow(RAW)
axes_image = viz.imshow_rand(automated_seg, alpha=0.4, axis=ax[1, 1])
ax[1, 2].imshow(RAW)
viz.imshow_rand(automated_seg, alpha=0.4, axis=ax[1, 2])
ax[0, 0].set_title(
"Worst merge comps colored by VI error: click to show them on second panel."
)
ax[0, 1].set_title("Worst merge comps.")
ax[0, 2].set_title("Ground Truth.")
ax[1, 0].set_title(
"Worst split comps colored by VI error: click to show them on second panel."
)
ax[1, 1].set_title("Worst split comps.")
ax[1, 2].set_title("Automated Seg.")
@jit
def drawer(seg, comps, limit=True):
"""Dynamically redraw the worst split/merge comps."""
a_seg = np.zeros_like(seg.astype('float64'))
factor = (seg.max() // num_elem)
lim = 0.0
for i, (j, k, z) in enumerate(comps):
lim += k
# if the area of the component is too small, we don't want to show it.
if z < 0.01:
continue
a_seg += (seg == j) * ((i + 1) * factor)
if limit:
# Limit the number of components that are shown.
if lim >= 0.98:
break
return a_seg
@jit
def _onpress(event):
"""Matplotlib 'onpress' event handler."""
if not (event.inaxes == ax[1, 0] or event.inaxes == ax[0, 0]
or event.inaxes == ax[0, 2] or event.inaxes == ax[1, 2]):
fig.text(0.5,
0.5,
s="Must click on left or right axes to show comps!",
ha="center")
fig.canvas.draw_idle()
if event.inaxes == ax[0, 0] or event.inaxes == ax[0, 2]:
if event.button != 1:
return
for txt in fig.texts:
txt.set_visible(False)
fig.canvas.draw()
x, y = vint(event.xdata), vint(event.ydata)
# Identify the worst merge components that are being pointed at by the mouse click.
comps = ev.split_components(automated_seg[y, x],
cont,
axis=0,
num_elems=None)
# Create the image containing only the identified components.
new_seg_1 = drawer(gt, comps, limit=False)
# Update the image with the drawn components
axes_image_1.set_array(new_seg_1)
# Draw this new image with the highlighted components onto the screen.
fig.canvas.draw()
if event.inaxes == ax[1, 0] or event.inaxes == ax[1, 2]:
if event.button != 1:
return
for txt in fig.texts:
txt.set_visible(False)
fig.canvas.draw()
x, y = vint(event.xdata), vint(event.ydata)
# Identify the worst split components that are being pointed at by the mouse click.
comps = ev.split_components(gt[y, x], cont, axis=1, num_elems=None)
# Create the image containing only the identified components.
new_seg = drawer(automated_seg, comps)
# Update the image with the drawn components
axes_image.set_array(new_seg)
# Draw this new image with the highlighted components onto the screen.
fig.canvas.draw()
fig.canvas.mpl_connect('button_press_event', _onpress)
plt.ioff()
plt.show()
