def test_calculate_probability_image_given_hypothesis(self):
fwm = i3d_vfm.VisionForwardModel(render_size=(200, 200), offscreen_rendering=True, custom_lighting=False)
# create a cube, this will be our sample
s = Shape(forward_model=fwm, viewpoint=[np.array([np.sqrt(8.0), 0.0, 90.0])],
params={'MAX_PIXEL_VALUE': 255.0, 'LL_VARIANCE': 0.1},
parts=[CuboidPrimitive(position=[0.0, 0.0, 0.0], size=[1.0, 1.0, 1.0])])
# observed image
image = np.load('test_images/test_image.npy')
# calculate logp(image|sample)
logp, logp_max = calculate_probability_image_given_hypothesis(image, s)
# these are pre-calculated. NOTE these could change if VisionForwardModel changes.
self.assertAlmostEqual(logp, -0.60814961737968254)
self.assertAlmostEqual(logp_max, 0.0)
# calculate logp(blank image|sample)
image = np.zeros((1, 200, 200))
logp, logp_max = calculate_probability_image_given_hypothesis(image, s)
self.assertAlmostEqual(logp, -1.5146551964550277)
self.assertAlmostEqual(logp_max, -0.91822996736329843)
# change ll_variance and see if logp_max changes accordingly
s.params['LL_VARIANCE'] = 0.01
logp, logp_max = calculate_probability_image_given_hypothesis(image, s)
self.assertAlmostEqual(logp_max / 10.0, -0.91822996736329843)
def test_calculate_probability_image_given_hypothesis(self):
fwm = i3d_vfm.VisionForwardModel(render_size=(200, 200),
offscreen_rendering=True,
custom_lighting=False)
# create a cube, this will be our sample
s = Shape(forward_model=fwm,
viewpoint=[np.array([np.sqrt(8.0), 0.0, 90.0])],
params={
'MAX_PIXEL_VALUE': 255.0,
'LL_VARIANCE': 0.1
},
parts=[
CuboidPrimitive(position=[0.0, 0.0, 0.0],
size=[1.0, 1.0, 1.0])
])
# observed image
image = np.load('test_images/test_image.npy')
# calculate logp(image|sample)
logp, logp_max = calculate_probability_image_given_hypothesis(image, s)
# these are pre-calculated. NOTE these could change if VisionForwardModel changes.
self.assertAlmostEqual(logp, -0.60814961737968254)
self.assertAlmostEqual(logp_max, 0.0)
# calculate logp(blank image|sample)
image = np.zeros((1, 200, 200))
logp, logp_max = calculate_probability_image_given_hypothesis(image, s)
self.assertAlmostEqual(logp, -1.5146551964550277)
self.assertAlmostEqual(logp_max, -0.91822996736329843)
# change ll_variance and see if logp_max changes accordingly
s.params['LL_VARIANCE'] = 0.01
logp, logp_max = calculate_probability_image_given_hypothesis(image, s)
self.assertAlmostEqual(logp_max / 10.0, -0.91822996736329843)
def test_render_cube_no_lighting(self):
# test object
part1 = CuboidPrimitive([0.0, 0.0, 0.0], [1.0, 1.0, 1.0])
s = Shape(forward_model=None, parts=[part1])
r = self.fwm_no_lighting.render(s)
correct = np.load('test_images/cube_no_lighting.npy')
self.assertAlmostEqual(np.sum(np.abs(r - correct)), 0.0)
# test changing viewpoint
for i, pos in enumerate(self.camera_pos):
s.viewpoint = [pos]
r = self.fwm_no_lighting.render(s)
self.assertAlmostEqual(np.sum(np.abs(r - correct[i])), 0.0)
def test_render_cube_no_lighting(self):
# test object
part1 = CuboidPrimitive([0.0, 0.0, 0.0], [1.0, 1.0, 1.0])
s = Shape(forward_model=None, parts=[part1])
r = self.fwm_no_lighting.render(s)
correct = np.load('test_images/cube_no_lighting.npy')
self.assertAlmostEqual(np.sum(np.abs(r - correct)), 0.0)
# test changing viewpoint
for i, pos in enumerate(self.camera_pos):
s.viewpoint = [pos]
r = self.fwm_no_lighting.render(s)
self.assertAlmostEqual(np.sum(np.abs(r - correct[i])), 0.0)
def test_calculate_similarity_image_given_image(self):
fwm = i3d_vfm.VisionForwardModel(render_size=(200, 200),
offscreen_rendering=True,
custom_lighting=False)
# create two samples
s1 = Shape(forward_model=fwm,
viewpoint=[np.array([np.sqrt(8.0), 0.0, 90.0])],
params={
'MAX_PIXEL_VALUE': 255.0,
'LL_VARIANCE': 0.1
},
parts=[
CuboidPrimitive(position=[0.0, 0.0, 0.0],
size=[1.0, 1.0, 1.0])
])
s2 = Shape(forward_model=fwm,
viewpoint=[np.array([np.sqrt(8.0), 0.0, 90.0])],
params={
'MAX_PIXEL_VALUE': 255.0,
'LL_VARIANCE': 0.1
},
parts=[
CuboidPrimitive(position=[0.0, 0.0, 0.0],
size=[.5, .5, .5])
])
# observed image
image = np.load('test_images/test_image.npy')
# calculate similarity using two samples
logp_avg, logp_wavg, logp_best, logp_wbest = calculate_similarity_image_given_image(
image, [s1, s2], [np.log(2.0), np.log(1.0)])
# these are pre-calculated. NOTE these could change if VisionForwardModel changes.
self.assertAlmostEqual(logp_avg, np.log(0.3549830885871178))
self.assertAlmostEqual(logp_wavg, np.log(0.41810779467381104))
self.assertAlmostEqual(logp_best, np.log(0.58679820659933835))
self.assertAlmostEqual(logp_wbest, np.log(0.72453213773289238))
# calculate similarity from one sample
logp_avg, logp_wavg, logp_best, logp_wbest = calculate_similarity_image_given_image(
image, [s1], [np.log(2.0)])
# these are pre-calculated. NOTE these could change if VisionForwardModel changes.
self.assertAlmostEqual(logp_avg, np.log(0.54435720684719735))
self.assertAlmostEqual(logp_wavg, np.log(0.54435720684719735))
self.assertAlmostEqual(logp_best, np.log(1.0))
self.assertAlmostEqual(logp_wbest, np.log(1.0))
def test_render_cube_custom_lighting(self):
# test object
part1 = CuboidPrimitive([0.0, 0.0, 0.0], [1.0, 1.0, 1.0])
s = Shape(forward_model=None, parts=[part1])
r = self.fwm_custom_lighting.render(s)
correct = np.load('test_images/cube_custom_lighting.npy')
self.assertAlmostEqual(np.sum(np.abs(r - correct)), 0.0)
# maximum intensity value for custom lighting should be around 174-175. This value is used in our likelihood
# calculations; therefore, it is important to make sure that it does not change.
self.assertTrue(175.0 > np.max(r) > 174.0)
# test changing viewpoint
for i, pos in enumerate(self.camera_pos):
s.viewpoint = [pos]
r = self.fwm_custom_lighting.render(s)
self.assertAlmostEqual(np.sum(np.abs(r - correct[i])), 0.0)
def test_render_cube_custom_lighting(self):
# test object
part1 = CuboidPrimitive([0.0, 0.0, 0.0], [1.0, 1.0, 1.0])
s = Shape(forward_model=None, parts=[part1])
r = self.fwm_custom_lighting.render(s)
correct = np.load('test_images/cube_custom_lighting.npy')
self.assertAlmostEqual(np.sum(np.abs(r - correct)), 0.0)
# maximum intensity value for custom lighting should be around 174-175. This value is used in our likelihood
# calculations; therefore, it is important to make sure that it does not change.
self.assertTrue(175.0 > np.max(r) > 174.0)
# test changing viewpoint
for i, pos in enumerate(self.camera_pos):
s.viewpoint = [pos]
r = self.fwm_custom_lighting.render(s)
self.assertAlmostEqual(np.sum(np.abs(r - correct[i])), 0.0)
def test_render_cube_object_no_lighting(self):
# test object
part1 = CuboidPrimitive([0.0, 0.0, 0.0], [0.8, 1.0, 0.4])
part2 = CuboidPrimitive([0.6, 0.0, 0.0], [0.4, 0.4, 0.3])
part3 = CuboidPrimitive([0.0, 0.0, 0.50], [0.2, 0.6, 0.6])
s = Shape(forward_model=None, parts=[part1, part2, part3])
r = self.fwm_no_lighting.render(s)
correct = np.load('test_images/cube_object_no_lighting.npy')
self.assertAlmostEqual(np.sum(np.abs(r - correct)), 0.0)
def test_save_render(self):
# test object
part1 = CuboidPrimitive([0.0, 0.0, 0.0], [0.8, 1.0, 0.4])
part2 = CuboidPrimitive([0.6, 0.0, 0.0], [0.4, 0.4, 0.3])
part3 = CuboidPrimitive([0.0, 0.0, 0.50], [0.2, 0.6, 0.6])
s = Shape(forward_model=None, parts=[part1, part2, part3])
self.fwm_custom_lighting.save_render('test_images/r.png', s)
for i in range(len(self.fwm_custom_lighting.camera_pos)):
r = spi.imread('test_images/r_{0:d}.png'.format(i))
correct = spi.imread(
'test_images/cube_object_custom_lighting_{0:d}.png'.format(i))
self.assertAlmostEqual(np.sum(np.abs(r - correct)), 0.0)
os.remove('test_images/r_{0:d}.png'.format(i))
def test_render_blank(self):
# blank image
s = Shape(forward_model=None, parts=[])
r = self.fwm_no_lighting.render(s)
self.assertTupleEqual(r.shape, (40, 200, 200))
self.assertAlmostEqual(np.sum(r), 0.0)
