def estimate_image(msi, regressor):
"""given an Msi and an regressor estimate the parmaeters for this image
Paramters:
msi: multi spectral image
regressor: regressor, must implement the predict method"""
# estimate parameters
collapsed_msi = imgmani.collapse_image(msi.get_image())
# in case of nan values: set to 0
collapsed_msi[np.isnan(collapsed_msi)] = 0.
collapsed_msi[np.isinf(collapsed_msi)] = 0.
start = time.time()
estimated_parameters = regressor.predict(collapsed_msi)
end = time.time()
estimation_time = end - start
logging.info("time necessary for estimating image parameters: " +
str(estimation_time) + "s")
# restore shape
feature_dimension = 1
if len(estimated_parameters.shape) > 1:
feature_dimension = estimated_parameters.shape[-1]
estimated_paramters_as_image = np.reshape(
estimated_parameters, (msi.get_image().shape[0],
msi.get_image().shape[1],
feature_dimension))
# save as sitk nrrd.
sitk_img = sitk.GetImageFromArray(estimated_paramters_as_image,
isVector=True)
return sitk_img, estimation_time
def estimate_image(msi, regressor):
"""given an Msi and an regressor estimate the parmaeters for this image
Paramters:
msi: multi spectral image
regressor: regressor, must implement the predict method"""
# estimate parameters
collapsed_msi = imgmani.collapse_image(msi.get_image())
# in case of nan values: set to 0
collapsed_msi[np.isnan(collapsed_msi)] = 0.
collapsed_msi[np.isinf(collapsed_msi)] = 0.
start = time.time()
estimated_parameters = regressor.predict(collapsed_msi)
end = time.time()
estimation_time = end - start
logging.info("time necessary for estimating image parameters: " +
str(estimation_time) + "s")
# restore shape
feature_dimension = 1
if len(estimated_parameters.shape) > 1:
feature_dimension = estimated_parameters.shape[-1]
estimated_paramters_as_image = np.reshape(
estimated_parameters, (msi.get_image().shape[0],
msi.get_image().shape[1],
feature_dimension))
# save as sitk nrrd.
sitk_img = sitk.GetImageFromArray(estimated_paramters_as_image,
isVector=True)
return sitk_img, estimation_time
def test_collapse_image(self):
image = self.image
newShapedImage = imgmani.collapse_image(image)
self.assertEqual(newShapedImage.shape,
(image.shape[0] * image.shape[1], image.shape[2]),
"collapsed image has correct shape")
np.testing.assert_equal(newShapedImage[2 * 5 + 2, :],
self.msi.get_image()[2, 2, :],
"values have been correctly transformed")
def test_collapse_image(self):
image = self.image
newShapedImage = imgmani.collapse_image(image)
self.assertEqual(newShapedImage.shape,
(image.shape[0] * image.shape[1], image.shape[2]),
"collapsed image has correct shape")
np.testing.assert_equal(newShapedImage[2 * 5 + 2, :],
self.msi.get_image()[2, 2, :],
"values have been correctly transformed")
def estimate_image_tensorflow(msi, model_checkpoint_dir):
# estimate parameters
collapsed_msi = imgmani.collapse_image(msi.get_image())
# in case of nan values: set to 0
collapsed_msi[np.isnan(collapsed_msi)] = 0.
collapsed_msi[np.isinf(collapsed_msi)] = 0.
tf.reset_default_graph()
keep_prob = tf.placeholder("float")
nr_wavelengths = len(msi.get_wavelengths())
x = tf.placeholder("float", [None, nr_wavelengths, 1, 1])
x_test_image = np.reshape(msi.get_image(), [-1, nr_wavelengths, 1, 1])
# Construct the desired model
# pred, regularizers = multilayer_perceptron(x, nr_wavelengths, 100, 1,
# keep_prob)
pred = cnn(x, 1, keep_prob)
# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
# restore model:
ckpt = tf.train.get_checkpoint_state(model_checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
start = time.time()
estimated_parameters = pred.eval({x: x_test_image,
keep_prob:1.0})
end = time.time()
estimation_time = end - start
logging.info("time necessary for estimating image parameters: " +
str(estimation_time) + "s")
# restore shape
feature_dimension = 1
if len(estimated_parameters.shape) > 1:
feature_dimension = estimated_parameters.shape[-1]
estimated_paramters_as_image = np.reshape(
estimated_parameters, (msi.get_image().shape[0],
msi.get_image().shape[1],
feature_dimension))
# save as sitk nrrd.
sitk_img = sitk.GetImageFromArray(estimated_paramters_as_image,
isVector=True)
return sitk_img, estimation_time
def estimate_image_tensorflow(msi, model_checkpoint_dir):
# estimate parameters
collapsed_msi = imgmani.collapse_image(msi.get_image())
# in case of nan values: set to 0
collapsed_msi[np.isnan(collapsed_msi)] = 0.
collapsed_msi[np.isinf(collapsed_msi)] = 0.
tf.reset_default_graph()
keep_prob = tf.placeholder("float")
nr_wavelengths = len(msi.get_wavelengths())
x = tf.placeholder("float", [None, nr_wavelengths, 1, 1])
x_test_image = np.reshape(msi.get_image(), [-1, nr_wavelengths, 1, 1])
# Construct the desired model
# pred, regularizers = multilayer_perceptron(x, nr_wavelengths, 100, 1,
# keep_prob)
pred = cnn(x, 1, keep_prob)
# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
# restore model:
ckpt = tf.train.get_checkpoint_state(model_checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
start = time.time()
estimated_parameters = pred.eval({x: x_test_image,
keep_prob:1.0})
end = time.time()
estimation_time = end - start
logging.info("time necessary for estimating image parameters: " +
str(estimation_time) + "s")
# restore shape
feature_dimension = 1
if len(estimated_parameters.shape) > 1:
feature_dimension = estimated_parameters.shape[-1]
estimated_paramters_as_image = np.reshape(
estimated_parameters, (msi.get_image().shape[0],
msi.get_image().shape[1],
feature_dimension))
# save as sitk nrrd.
sitk_img = sitk.GetImageFromArray(estimated_paramters_as_image,
isVector=True)
return sitk_img, estimation_time
def test_collapse_image_retains_data(self):
newShapedImage = imgmani.collapse_image(self.image)
self.msi.get_image()[2, 2, 0] = 5000.
self.assertEqual(newShapedImage[2 * 5 + 2, 0], 5000.,
"collapse_image does not copy data")
def test_collapse_image_retains_data(self):
newShapedImage = imgmani.collapse_image(self.image)
self.msi.get_image()[2, 2, 0] = 5000.
self.assertEqual(newShapedImage[2 * 5 + 2, 0], 5000.,
"collapse_image does not copy data")