def test_DATAGENERATOR_runTraining(self):
pp_fi = Preprocessor(self.data_io,
batch_size=4,
data_aug=self.data_aug,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=None)
self.assertEqual(len(data_gen), 3)
for batch in data_gen:
self.assertIsInstance(batch, tuple)
self.assertEqual(batch[0].shape, (4, 16, 16, 16, 1))
self.assertEqual(batch[1].shape, (4, 16, 16, 16, 3))
pp_pc = Preprocessor(self.data_io,
batch_size=3,
data_aug=self.data_aug,
prepare_subfunctions=False,
prepare_batches=False,
patch_shape=(5, 5, 5),
analysis="patchwise-crop")
data_gen = DataGenerator(self.sample_list,
pp_pc,
training=True,
shuffle=False,
iterations=None)
self.assertEqual(len(data_gen), 4)
for batch in data_gen:
self.assertIsInstance(batch, tuple)
self.assertEqual(batch[0].shape, (3, 5, 5, 5, 1))
self.assertEqual(batch[1].shape, (3, 5, 5, 5, 3))
def test_SUBFUNCTIONS_preprocessing(self):
ds = dict()
for i in range(0, 10):
img = np.random.rand(16, 16, 16) * 255
img = img.astype(int)
seg = np.random.rand(16, 16, 16) * 3
seg = seg.astype(int)
sample = (img, seg)
ds["TEST.sample_" + str(i)] = sample
io_interface = Dictionary_interface(ds, classes=3, three_dim=True)
self.tmp_dir = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir.name, "batches")
dataio = Data_IO(io_interface, input_path="", output_path="",
batch_path=tmp_batches, delete_batchDir=False)
sf = [Resize((8,8,8)), Normalization(), Clipping(min=-1.0, max=0.0)]
pp = Preprocessor(dataio, data_aug=None, batch_size=1,
prepare_subfunctions=False, analysis="fullimage",
subfunctions=sf)
sample_list = dataio.get_indiceslist()
batches = pp.run(sample_list, training=True, validation=False)
for i in range(0, 10):
img = batches[i][0]
seg = batches[i][1]
self.assertEqual(img.shape, (1,8,8,8,1))
self.assertEqual(seg.shape, (1,8,8,8,3))
self.assertTrue(np.min(img) >= -1.0 and np.max(img) <= 0.0)
self.tmp_dir.cleanup()
def setUpClass(self):
np.random.seed(1234)
# Create 2D imgaging and segmentation data set
self.dataset2D = dict()
for i in range(0, 6):
img = np.random.rand(16, 16) * 255
self.img = img.astype(int)
seg = np.random.rand(16, 16) * 3
self.seg = seg.astype(int)
self.dataset2D["TEST.sample_" + str(i)] = (self.img, self.seg)
# Initialize Dictionary IO Interface
io_interface2D = Dictionary_interface(self.dataset2D,
classes=3,
three_dim=False)
# Initialize temporary directory
self.tmp_dir2D = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir2D.name, "batches")
# Initialize Data IO
self.data_io2D = Data_IO(io_interface2D,
input_path=os.path.join(self.tmp_dir2D.name),
output_path=os.path.join(self.tmp_dir2D.name),
batch_path=tmp_batches,
delete_batchDir=False)
# Initialize Preprocessor
self.pp2D = Preprocessor(self.data_io2D,
batch_size=2,
data_aug=None,
analysis="fullimage")
# Get sample list
self.sample_list2D = self.data_io2D.get_indiceslist()
# Create 3D imgaging and segmentation data set
self.dataset3D = dict()
for i in range(0, 6):
img = np.random.rand(16, 16, 16) * 255
self.img = img.astype(int)
seg = np.random.rand(16, 16, 16) * 3
self.seg = seg.astype(int)
self.dataset3D["TEST.sample_" + str(i)] = (self.img, self.seg)
# Initialize Dictionary IO Interface
io_interface3D = Dictionary_interface(self.dataset3D,
classes=3,
three_dim=True)
# Initialize temporary directory
self.tmp_dir3D = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir3D.name, "batches")
# Initialize Data IO
self.data_io3D = Data_IO(io_interface3D,
input_path=os.path.join(self.tmp_dir3D.name),
output_path=os.path.join(self.tmp_dir3D.name),
batch_path=tmp_batches,
delete_batchDir=False)
# Initialize Preprocessor
self.pp3D = Preprocessor(self.data_io3D,
batch_size=2,
data_aug=None,
analysis="fullimage")
# Get sample list
self.sample_list3D = self.data_io3D.get_indiceslist()
def test_PREPROCESSOR_BASE_dataaugmentation(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D, batch_size=1, analysis="fullimage")
batches = pp.run(sample_list[8:10], training=False, validation=False)
self.assertEqual(len(batches), 2)
self.assertEqual(batches[0][0].shape, (1, 16, 16, 16, 1))
self.assertIsNone(batches[0][1])
sample = self.data_io3D.sample_loader(sample_list[8], load_seg=False)
self.assertFalse(np.array_equal(batches[0][0], sample.img_data))
def test_PREPROCESSOR_BASE_prepareSubfunctions(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
batch_size=1,
analysis="fullimage",
prepare_subfunctions=True)
pp.run_subfunctions(sample_list[0:8], training=True)
pp.run(sample_list[0:8], training=True, validation=False)
pp.run_subfunctions(sample_list[8:10], training=False)
pp.run(sample_list[8:10], training=False, validation=False)
def test_PREPROCESSOR_BASE_create(self):
with self.assertRaises(Exception):
Preprocessor()
Preprocessor(self.data_io3D, batch_size=1, analysis="fullimage")
Preprocessor(self.data_io3D,
batch_size=1,
analysis="patchwise-crop",
patch_shape=(16, 16, 16))
Preprocessor(self.data_io3D,
batch_size=1,
analysis="patchwise-grid",
patch_shape=(16, 16, 16),
data_aug=None)
def test_PREPROCESSOR_postprocessing_(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
batch_size=1,
analysis="fullimage",
data_aug=None)
batches = pp.run(sample_list[0:3], training=True, validation=False)
for i in range(0, 3):
pred_postprec = pp.postprocessing(sample_list[i], batches[i][1])
self.assertEqual(pred_postprec.shape, (16, 16, 16))
sam = self.data_io3D.sample_loader(sample_list[i], load_seg=True)
self.assertTrue(
np.array_equal(pred_postprec,
np.reshape(sam.seg_data, (16, 16, 16))))
def test_PREPROCESSOR_patchwisecrop_skipBlanks(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
data_aug=None,
batch_size=1,
analysis="patchwise-crop",
patch_shape=(4, 4, 4))
pp.patchwise_skip_blanks = True
batches = pp.run(sample_list[0:3], training=True, validation=False)
sample = self.data_io3D.sample_loader(sample_list[0], load_seg=True)
sample.seg_data = to_categorical(sample.seg_data,
num_classes=sample.classes)
ready_data = pp.analysis_patchwise_crop(sample, data_aug=False)
self.assertEqual(len(ready_data), 1)
self.assertEqual(ready_data[0][0].shape, (4, 4, 4, 1))
self.assertEqual(ready_data[0][1].shape, (4, 4, 4, 3))
def test_PREPROCESSOR_BASE_prepareBatches(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
batch_size=1,
analysis="fullimage",
prepare_batches=True)
batch_pointer = pp.run(sample_list[0:8],
training=True,
validation=False)
self.assertEqual(batch_pointer, 7)
tmp_batches = os.path.join(self.tmp_dir3D.name, "batches")
batch_list = []
for batch_file in os.listdir(tmp_batches):
if batch_file.startswith(str(pp.data_io.seed)):
batch_list.append(batch_file)
self.assertEqual(len(batch_list), 16)
def test_PREPROCESSOR_BASE_run(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
data_aug=None,
batch_size=1,
analysis="fullimage")
batches = pp.run(sample_list[8:10], training=False, validation=False)
self.assertEqual(len(batches), 2)
self.assertEqual(batches[0][0].shape, (1, 16, 16, 16, 1))
self.assertIsNone(batches[0][1])
batches = pp.run(sample_list[0:8], training=True, validation=False)
self.assertEqual(batches[0][0].shape, (1, 16, 16, 16, 1))
self.assertEqual(batches[0][1].shape, (1, 16, 16, 16, 3))
batches = pp.run(sample_list[0:8], training=True, validation=True)
self.assertEqual(batches[0][0].shape, (1, 16, 16, 16, 1))
self.assertEqual(batches[0][1].shape, (1, 16, 16, 16, 3))
def setUpClass(self):
np.random.seed(1234)
# Create 2D imgaging and segmentation data set
self.dataset = dict()
for i in range(0, 2):
img = np.random.rand(16, 16) * 255
self.img = img.astype(int)
seg = np.random.rand(16, 16) * 2
self.seg = seg.astype(int)
self.dataset["TEST.sample_" + str(i)] = (self.img, self.seg)
# Initialize Dictionary IO Interface
io_interface = Dictionary_interface(self.dataset, classes=3,
three_dim=False)
# Initialize temporary directory
self.tmp_dir = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir.name, "batches")
# Initialize Data IO
self.data_io = Data_IO(io_interface,
input_path=os.path.join(self.tmp_dir.name),
output_path=os.path.join(self.tmp_dir.name),
batch_path=tmp_batches, delete_batchDir=False)
# Initialize Preprocessor
self.pp = Preprocessor(self.data_io, batch_size=1,
data_aug=None, analysis="fullimage")
# Initialize Neural Network
self.model = Neural_Network(self.pp)
# Get sample list
self.sample_list = self.data_io.get_indiceslist()
def test_DATAGENERATOR_iterations(self):
pp_fi = Preprocessor(self.data_io,
batch_size=1,
data_aug=None,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=None)
self.assertEqual(10, len(data_gen))
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=5)
self.assertEqual(5, len(data_gen))
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=50)
self.assertEqual(50, len(data_gen))
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=100)
self.assertEqual(100, len(data_gen))
def test_EVALUATION_leaveOneOut(self):
# Create 3D imgaging and segmentation data set
self.dataset3D = dict()
for i in range(0, 6):
img = np.random.rand(16, 16, 16) * 255
self.img = img.astype(int)
seg = np.random.rand(16, 16, 16) * 3
self.seg = seg.astype(int)
self.dataset3D["TEST.sample_" + str(i)] = (self.img, self.seg)
# Initialize Dictionary IO Interface
io_interface3D = Dictionary_interface(self.dataset3D, classes=3,
three_dim=True)
# Initialize temporary directory
self.tmp_dir3D = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir3D.name, "batches")
# Initialize Data IO
self.data_io3D = Data_IO(io_interface3D,
input_path=os.path.join(self.tmp_dir3D.name),
output_path=os.path.join(self.tmp_dir3D.name),
batch_path=tmp_batches, delete_batchDir=False)
# Initialize Preprocessor
self.pp3D = Preprocessor(self.data_io3D, batch_size=2,
data_aug=None, analysis="fullimage")
# Initialize Neural Network
model = Neural_Network(self.pp3D)
# Get sample list
self.sample_list3D = self.data_io3D.get_indiceslist()
eval_path = os.path.join(self.tmp_dir3D.name, "evaluation")
leave_one_out(self.sample_list3D, model, epochs=3, iterations=None,
evaluation_path=eval_path, callbacks=[])
self.assertTrue(os.path.exists(eval_path))
# Cleanup stuff
self.tmp_dir3D.cleanup()
def test_SUBFUNCTIONS_postprocessing(self):
ds = dict()
for i in range(0, 10):
img = np.random.rand(16, 16, 16) * 255
img = img.astype(int)
seg = np.random.rand(16, 16, 16) * 3
seg = seg.astype(int)
sample = (img, seg)
ds["TEST.sample_" + str(i)] = sample
io_interface = Dictionary_interface(ds, classes=3, three_dim=True)
self.tmp_dir = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir.name, "batches")
dataio = Data_IO(io_interface,
input_path="",
output_path="",
batch_path=tmp_batches,
delete_batchDir=False)
sf = [Resize((9, 9, 9)), Normalization(), Clipping(min=-1.0, max=0.0)]
pp = Preprocessor(dataio,
batch_size=1,
prepare_subfunctions=False,
analysis="patchwise-grid",
subfunctions=sf,
patch_shape=(4, 4, 4))
sample_list = dataio.get_indiceslist()
for index in sample_list:
sample = dataio.sample_loader(index)
for sf in pp.subfunctions:
sf.preprocessing(sample, training=False)
pp.cache["shape_" + str(index)] = sample.img_data.shape
sample.seg_data = np.random.rand(9, 9, 9) * 3
sample.seg_data = sample.seg_data.astype(int)
sample.seg_data = to_categorical(sample.seg_data, num_classes=3)
data_patches = pp.analysis_patchwise_grid(sample,
training=True,
data_aug=False)
seg_list = []
for i in range(0, len(data_patches)):
seg_list.append(data_patches[i][1])
seg = np.stack(seg_list, axis=0)
self.assertEqual(seg.shape, (27, 4, 4, 4, 3))
pred = pp.postprocessing(sample, seg)
self.assertEqual(pred.shape, (16, 16, 16))
self.tmp_dir.cleanup()
def test_PREPROCESSOR_fullimage_3D(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
data_aug=None,
batch_size=2,
analysis="fullimage")
batches = pp.run(sample_list[0:3], training=True, validation=False)
self.assertEqual(len(batches), 2)
batches = pp.run(sample_list[0:1], training=False, validation=False)
self.assertEqual(len(batches), 1)
sample = self.data_io3D.sample_loader(sample_list[0], load_seg=True)
sample.seg_data = to_categorical(sample.seg_data,
num_classes=sample.classes)
ready_data = pp.analysis_fullimage(sample,
data_aug=False,
training=True)
self.assertEqual(len(ready_data), 1)
self.assertEqual(ready_data[0][0].shape, (16, 16, 16, 1))
self.assertEqual(ready_data[0][1].shape, (16, 16, 16, 3))
def test_MODEL_predictionAugmentated_2D(self):
data_aug = Data_Augmentation()
pp = Preprocessor(self.data_io2D,
batch_size=2,
data_aug=data_aug,
analysis="fullimage")
nn = Neural_Network(preprocessor=pp)
for sample in self.sample_list2D:
predictions = nn.predict_augmentated(sample)
self.assertEqual(len(predictions), 2)
for pred in predictions:
self.assertEqual(pred.shape, (16, 16, 3))
def test_SUBFUNCTIONS_prepare_MULTIPROCESSING(self):
ds = dict()
for i in range(0, 5):
img = np.random.rand(16, 16, 16) * 255
img = img.astype(int)
seg = np.random.rand(16, 16, 16) * 3
seg = seg.astype(int)
sample = (img, seg)
ds["TEST.sample_" + str(i)] = sample
io_interface = Dictionary_interface(ds, classes=3, three_dim=True)
self.tmp_dir = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir.name, "batches")
dataio = Data_IO(io_interface, input_path="", output_path="",
batch_path=tmp_batches, delete_batchDir=False)
sf = [Resize((8,8,8)), Normalization(), Clipping(min=-1.0, max=0.0)]
pp = Preprocessor(dataio, batch_size=1, prepare_subfunctions=True,
analysis="fullimage", subfunctions=sf,
use_multiprocessing=True)
pp.mp_threads = 4
sample_list = dataio.get_indiceslist()
pp.run_subfunctions(sample_list, training=True)
batches = pp.run(sample_list, training=True, validation=False)
self.assertEqual(len(os.listdir(tmp_batches)), 5)
for i in range(0, 5):
file_prepared_subfunctions = os.path.join(tmp_batches,
str(pp.data_io.seed) + ".TEST.sample_" + str(i) + ".pickle")
self.assertTrue(os.path.exists(file_prepared_subfunctions))
img = batches[i][0]
seg = batches[i][1]
self.assertIsNotNone(img)
self.assertIsNotNone(seg)
self.assertEqual(img.shape, (1,8,8,8,1))
self.assertEqual(seg.shape, (1,8,8,8,3))
def test_MODEL_predictionAugmentated_3D(self):
data_aug = Data_Augmentation()
pp = Preprocessor(self.data_io3D,
batch_size=1,
patch_shape=(8, 8, 8),
data_aug=data_aug,
analysis="patchwise-crop")
nn = Neural_Network(preprocessor=pp,
architecture=UNet_standard(depth=2))
for sample in self.sample_list3D:
predictions = nn.predict_augmentated(sample)
self.assertEqual(len(predictions), 3)
for pred in predictions:
self.assertEqual(pred.shape, (16, 16, 16, 3))
def test_DATAGENERATOR_create(self):
pp_fi = Preprocessor(self.data_io,
batch_size=4,
data_aug=self.data_aug,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=False,
validation=False,
shuffle=False,
iterations=None)
self.assertIsInstance(data_gen, DataGenerator)
def test_DATAGENERATOR_shuffle(self):
pp_fi = Preprocessor(self.data_io,
batch_size=1,
data_aug=None,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=None)
list_ordered = []
for batch in data_gen:
list_ordered.append(batch)
for batch in data_gen:
list_ordered.append(batch)
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=True,
iterations=None)
list_shuffled = []
for batch in data_gen:
list_shuffled.append(batch)
data_gen.on_epoch_end()
for batch in data_gen:
list_shuffled.append(batch)
size = len(data_gen)
o_counter = 0
s_counter = 0
for i in range(0, size):
oa_img = list_ordered[i][0]
oa_seg = list_ordered[i][1]
ob_img = list_ordered[i + size][0]
ob_seg = list_ordered[i + size][1]
sa_img = list_shuffled[i][0]
sa_seg = list_shuffled[i][1]
sb_img = list_shuffled[i + size][0]
sb_seg = list_shuffled[i + size][1]
if np.array_equal(oa_img, ob_img) and \
np.array_equal(oa_seg, ob_seg):
o_counter += 1
if not np.array_equal(sa_img, sb_img) and \
not np.array_equal(sa_seg, sb_seg):
s_counter += 1
o_ratio = o_counter / size
self.assertTrue(o_ratio == 1.0)
s_ratio = s_counter / size
self.assertTrue(1.0 >= s_ratio and s_ratio >= 0.5)
def test_DATAGENERATOR_augcyling(self):
data_aug = Data_Augmentation(cycles=20)
pp_fi = Preprocessor(self.data_io,
batch_size=4,
data_aug=data_aug,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=None)
self.assertEqual(50, len(data_gen))
def test_DATAGENERATOR_prepareData(self):
pp_fi = Preprocessor(self.data_io,
batch_size=4,
data_aug=None,
prepare_subfunctions=True,
prepare_batches=True,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=True,
iterations=None)
self.assertEqual(len(data_gen), 3)
for batch in data_gen:
self.assertIsInstance(batch, tuple)
self.assertEqual(batch[0].shape[1:], (16, 16, 16, 1))
self.assertEqual(batch[1].shape[1:], (16, 16, 16, 3))
self.assertIn(batch[0].shape[0], [2, 4])
def test_SUBFUNCTIONS_fullrun(self):
ds = dict()
for i in range(0, 10):
img = np.random.rand(16, 16, 16) * 255
img = img.astype(int)
seg = np.random.rand(16, 16, 16) * 3
seg = seg.astype(int)
sample = (img, seg)
ds["TEST.sample_" + str(i)] = sample
io_interface = Dictionary_interface(ds, classes=3, three_dim=True)
self.tmp_dir = tempfile.TemporaryDirectory(prefix="tmp.miscnn.")
tmp_batches = os.path.join(self.tmp_dir.name, "batches")
dataio = Data_IO(io_interface, input_path="", output_path="",
batch_path=tmp_batches, delete_batchDir=False)
sf = [Resize((16,16,16)), Normalization(), Clipping(min=-1.0, max=0.0)]
pp = Preprocessor(dataio, batch_size=1, prepare_subfunctions=True,
analysis="fullimage", subfunctions=sf)
nn = Neural_Network(preprocessor=pp)
sample_list = dataio.get_indiceslist()
nn.predict(sample_list, return_output=True)
def test_DATAGENERATOR_consistency(self):
pp_fi = Preprocessor(self.data_io,
batch_size=1,
data_aug=None,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator(self.sample_list,
pp_fi,
training=True,
shuffle=False,
iterations=None)
i = 0
for batch in data_gen:
sample = self.data_io.sample_loader(self.sample_list[i],
load_seg=True)
self.assertTrue(np.array_equal(batch[0][0], sample.img_data))
seg = to_categorical(sample.seg_data, num_classes=3)
self.assertTrue(np.array_equal(batch[1][0], seg))
i += 1
def test_DATAGENERATOR_inferenceAug(self):
data_aug = Data_Augmentation()
pp_fi = Preprocessor(self.data_io,
batch_size=4,
data_aug=data_aug,
prepare_subfunctions=False,
prepare_batches=False,
analysis="fullimage")
data_gen = DataGenerator([self.sample_list[0]],
pp_fi,
training=False,
shuffle=False,
iterations=None)
pred_list_inactive = []
for batch in data_gen:
pred_list_inactive.append(batch)
data_aug.infaug = True
pred_list_active = []
for batch in data_gen:
pred_list_active.append(batch)
for i in range(0, len(pred_list_active)):
ba = pred_list_active[i]
bi = pred_list_inactive[i]
self.assertFalse(np.array_equal(ba, bi))
def test_PREPROCESSOR_patchwisegrid_3D(self):
sample_list = self.data_io3D.get_indiceslist()
pp = Preprocessor(self.data_io3D,
data_aug=None,
batch_size=1,
analysis="patchwise-grid",
patch_shape=(4, 4, 4))
batches = pp.run(sample_list[0:1], training=False, validation=False)
self.assertEqual(len(batches), 64)
sample = self.data_io3D.sample_loader(sample_list[0], load_seg=True)
sample.seg_data = to_categorical(sample.seg_data,
num_classes=sample.classes)
pp = Preprocessor(self.data_io3D,
data_aug=None,
batch_size=1,
analysis="patchwise-grid",
patch_shape=(5, 5, 5))
ready_data = pp.analysis_patchwise_grid(sample,
data_aug=False,
training=True)
self.assertEqual(len(ready_data), 64)
self.assertEqual(ready_data[0][0].shape, (5, 5, 5, 1))
self.assertEqual(ready_data[0][1].shape, (5, 5, 5, 3))
# Let's test out, if the the NIfTI slicer interface works like we want
# and output the image and segmentation shape of a random slice
sample = data_io.sample_loader("case_00002:#:42", load_seg=True)
print(sample.img_data.shape, sample.seg_data.shape)
## As you hopefully noted, the index of a slice is defined
## as the volume file name and the slice number separated with a ":#:"
# Specify subfunctions for preprocessing
## Here we are using the Resize subfunctions due to many 2D models
## want a specific shape (e.g. DenseNet for classification)
sf = [Resize(new_shape=(224, 224))]
# Initialize the Preprocessor class
pp = Preprocessor(data_io, data_aug=None, batch_size=1, subfunctions=sf,
prepare_subfunctions=True, prepare_batches=False,
analysis="fullimage")
## We are using fullimage analysis due to a 2D image can easily fit completely
## in our GPU
# Initialize the neural network model
model = Neural_Network(preprocessor=pp)
# Start the fitting on some slices
model.train(samples_list[30:50], epochs=3, iterations=10, callbacks=[])
# Predict a generic slice with direct output
pred = model.predict(["case_00002:#:42"], return_output=True)
print(np.asarray(pred).shape)
## Be aware that the direct prediction output, has a additional batch axis
def run(self):
# Create sample list for miscnn
util.create_sample_list(self.input_dir)
# Initialize Data IO Interface for NIfTI data
interface = NIFTI_interface(channels=1, classes=2)
# Create Data IO object to load and write samples in the file structure
data_io = Data_IO(interface,
input_path=self.input_dir,
delete_batchDir=False)
# Access all available samples in our file structure
sample_list = data_io.get_indiceslist()
sample_list.sort()
# Create a resampling Subfunction to voxel spacing 1.58 x 1.58 x 2.70
sf_resample = Resampling((1.58, 1.58, 2.70))
# Create a pixel value normalization Subfunction for z-score scaling
sf_zscore = Normalization(mode="z-score")
# Create a pixel value normalization Subfunction to scale between 0-255
sf_normalize = Normalization(mode="grayscale")
# Assemble Subfunction classes into a list
sf = [sf_normalize, sf_resample, sf_zscore]
# Create and configure the Preprocessor class
pp = Preprocessor(data_io,
batch_size=2,
subfunctions=sf,
prepare_subfunctions=True,
prepare_batches=False,
analysis="patchwise-crop",
patch_shape=(160, 160, 80))
# Adjust the patch overlap for predictions
pp.patchwise_overlap = (80, 80, 30)
# Initialize the Architecture
unet_standard = Architecture(depth=4,
activation="softmax",
batch_normalization=True)
# Create the Neural Network model
model = Neural_Network(
preprocessor=pp,
architecture=unet_standard,
loss=tversky_crossentropy,
metrics=[tversky_loss, dice_soft, dice_crossentropy],
batch_queue_size=3,
workers=1,
learninig_rate=0.001)
# Load best model weights during fitting
model.load(f'{self.model_dir}{self.model_name}.hdf5')
# Obtain training and validation data set ----- CHANGE BASED ON PRED/TRAIN
images, _ = load_disk2fold(f'{self.input_dir}sample_list.json')
print('\n\nRunning automatic segmentation on samples...\n')
print(f'Segmenting images: {images}')
# Compute predictions
self.predictions = model.predict(images)
# Delete folder created by miscnn
shutil.rmtree('batches/')
# Create a clipping Subfunction to the lung window of CTs (-1250 and 250)
sf_clipping = Clipping(min=-1250, max=250)
# Create a pixel value normalization Subfunction to scale between 0-255
sf_normalize = Normalization(mode="grayscale")
# Create a resampling Subfunction to voxel spacing 1.58 x 1.58 x 2.70
sf_resample = Resampling((1.58, 1.58, 2.70))
# Create a pixel value normalization Subfunction for z-score scaling
sf_zscore = Normalization(mode="z-score")
# Assemble Subfunction classes into a list
sf = [sf_clipping, sf_normalize, sf_resample, sf_zscore]
# Create and configure the Preprocessor class
pp = Preprocessor(data_io, data_aug=data_aug, batch_size=2, subfunctions=sf,
prepare_subfunctions=True, prepare_batches=False,
analysis="fullimage", patch_shape=(160, 160, 80))
# Adjust the patch overlap for predictions
pp.patchwise_overlap = (80, 80, 40)
# Initialize Keras Data Generator for generating batches
from miscnn.neural_network.data_generator import DataGenerator
dataGen = DataGenerator(sample_list, pp, training=False, validation=False, shuffle=False)
x = []
y = []
z = []
for batch in dataGen:
print("Batch:", batch.shape)
x.append(batch.shape[1])
# Create a pixel value normalization Subfunction to scale between 0-255
sf_normalize = Normalization(mode="grayscale")
# Create a resampling Subfunction to voxel spacing 1.58 x 1.58 x 2.70
sf_resample = Resampling((1.58, 1.58, 2.70))
# Create a pixel value normalization Subfunction for z-score scaling
sf_zscore = Normalization(mode="z-score")
# Assemble Subfunction classes into a list
sf = [sf_clipping, sf_normalize, sf_resample, sf_zscore]
# Create and configure the Preprocessor class
pp = Preprocessor(data_io,
data_aug=data_aug,
batch_size=2,
subfunctions=sf,
prepare_subfunctions=True,
prepare_batches=False,
analysis="patchwise-crop",
patch_shape=(160, 160, 80),
use_multiprocessing=True)
# Adjust the patch overlap for predictions
pp.patchwise_overlap = (80, 80, 30)
# Initialize the Architecture
unet_standard = Architecture(depth=4,
activation="softmax",
batch_normalization=True)
# Create the Neural Network model
model = Neural_Network(preprocessor=pp,
architecture=unet_standard,
