def test_tensorboard_save():
inp = torch.tensor(np.zeros((1, 1, 15, 15)))
gt = torch.tensor(np.zeros((1, 1, 15, 15)))
pred = torch.tensor(np.zeros((1, 1, 15, 15)))
dpath = Path(__tmp_dir__, "test_tensorboard_save")
dpath.mkdir(parents=True, exist_ok=True)
writer = SummaryWriter(log_dir=str(dpath))
imed_visualize.save_img(writer, 1, "Training", inp, pred, gt)
writer.flush()
summary_iterators = [EventAccumulator(str(dname)).Reload() for dname in dpath.iterdir()]
for i in range(len(summary_iterators)):
if summary_iterators[i].Tags()['images'] == ['Training/Input', 'Training/Predictions', 'Training/Ground Truth']:
input_retrieve = np.array(Image.open(io.BytesIO(summary_iterators[i].Images('Training/Input')[0][2])))
pred_retrieve = np.array(Image.open(io.BytesIO(summary_iterators[i].Images('Training/Predictions')[0][2])))
gt_retrieve = np.array(Image.open(io.BytesIO(summary_iterators[i].Images('Training/Ground Truth')[0][2])))
assert np.allclose(imed_math.rescale_values_array(input_retrieve[:, :, 0], 0, 1), inp[0, 0, :, :])
assert np.allclose(imed_math.rescale_values_array(pred_retrieve[:, :, 0], 0, 1), pred[0, 0, :, :])
assert np.allclose(imed_math.rescale_values_array(gt_retrieve[:, :, 0], 0, 1), gt[0, 0, :, :])
def test_tensorboard_save():
inp = torch.tensor(np.zeros((1, 1, 15, 15)))
gt = torch.tensor(np.zeros((1, 1, 15, 15)))
pred = torch.tensor(np.zeros((1, 1, 15, 15)))
dpath = "test_tensorboard_save"
os.makedirs(dpath)
writer = SummaryWriter(log_dir=dpath)
imed_utils.save_tensorboard_img(writer, 1, "Training", inp, pred, gt)
writer.flush()
summary_iterators = [
EventAccumulator(os.path.join(dpath, dname)).Reload()
for dname in os.listdir(dpath)
]
for i in range(len(summary_iterators)):
if summary_iterators[i].Tags()['images'] == [
'Training/Input', 'Training/Predictions',
'Training/Ground Truth'
]:
input_retrieve = np.array(
Image.open(
io.BytesIO(
summary_iterators[i].Images('Training/Input')[0][2])))
pred_retrieve = np.array(
Image.open(
io.BytesIO(summary_iterators[i].Images(
'Training/Predictions')[0][2])))
gt_retrieve = np.array(
Image.open(
io.BytesIO(summary_iterators[i].Images(
'Training/Ground Truth')[0][2])))
assert np.allclose(
imed_math.rescale_values_array(input_retrieve[:, :, 0], 0, 1),
inp[0, 0, :, :])
assert np.allclose(
imed_math.rescale_values_array(pred_retrieve[:, :, 0], 0, 1),
pred[0, 0, :, :])
assert np.allclose(
imed_math.rescale_values_array(gt_retrieve[:, :, 0], 0, 1),
gt[0, 0, :, :])
def run_visualization(input, config, number, output, roi):
"""Utility function to visualize Data Augmentation transformations.
Data augmentation is a key part of the Deep Learning training scheme. This script aims at facilitating the
fine-tuning of data augmentation parameters. To do so, this script provides a step-by-step visualization of the
transformations that are applied on data.
This function applies a series of transformations (defined in a configuration file
``-c``) to ``-n`` 2D slices randomly extracted from an input image (``-i``), and save as png the resulting sample
after each transform.
For example::
ivadomed_visualize_transforms -i t2s.nii.gz -n 1 -c config.json -r t2s_seg.nii.gz
Provides a visualization of a series of three transformation on a randomly selected slice:
.. image:: https://raw.githubusercontent.com/ivadomed/doc-figures/main/scripts/transforms_im.png
:width: 600px
:align: center
And on a binary mask::
ivadomed_visualize_transforms -i t2s_gmseg.nii.gz -n 1 -c config.json -r t2s_seg.nii.gz
Gives:
.. image:: https://raw.githubusercontent.com/ivadomed/doc-figures/main/scripts/transforms_gt.png
:width: 600px
:align: center
Args:
input (string): Image filename. Flag: ``--input``, ``-i``
config (string): Configuration file filename. Flag: ``--config``, ``-c``
number (int): Number of slices randomly extracted. Flag: ``--number``, ``-n``
output (string): Folder path where the results are saved. Flag: ``--ofolder``, ``-o``
roi (string): Filename of the region of interest. Only needed if ROICrop is part of the transformations.
Flag: ``--roi``, ``-r``
"""
# Load context
context = imed_config_manager.ConfigurationManager(config).get_config()
# Create output folder
if not Path(output).is_dir():
Path(output).mkdir(parents=True)
# Slice extracted according to below axis
axis = imed_utils.AXIS_DCT[context[ConfigKW.LOADER_PARAMETERS][LoaderParamsKW.SLICE_AXIS]]
# Get data
input_img, input_data = get_data(input, axis)
# Image or Mask
is_mask = np.array_equal(input_data, input_data.astype(bool))
# Get zooms
zooms = imed_loader_utils.orient_shapes_hwd(input_img.header.get_zooms(), slice_axis=axis)
# Get indexes
indexes = random.sample(range(0, input_data.shape[2]), number)
# Get training transforms
training_transforms, _, _ = imed_transforms.get_subdatasets_transforms(context[ConfigKW.TRANSFORMATION])
if TransformationKW.ROICROP in training_transforms:
if roi and Path(roi).is_file():
roi_img, roi_data = get_data(roi, axis)
else:
raise ValueError("\nPlease provide ROI image (-r) in order to apply ROICrop transformation.")
# Compose transforms
dict_transforms = {}
stg_transforms = ""
for transform_name in training_transforms:
# We skip NumpyToTensor transform since that s only a change of data type
if transform_name == "NumpyToTensor":
continue
# Update stg_transforms
stg_transforms += transform_name + "_"
# Add new transform to Compose
dict_transforms.update({transform_name: training_transforms[transform_name]})
composed_transforms = imed_transforms.Compose(dict_transforms)
# Loop across slices
for i in indexes:
data = [input_data[:, :, i]]
# Init metadata
metadata = SampleMetadata({MetadataKW.ZOOMS: zooms, MetadataKW.DATA_TYPE: "gt" if is_mask else "im"})
# Apply transformations to ROI
if TransformationKW.CENTERCROP in training_transforms or \
(TransformationKW.ROICROP in training_transforms and Path(roi).is_file()):
metadata.__setitem__(MetadataKW.CROP_PARAMS, {})
# Apply transformations to image
stack_im, _ = composed_transforms(sample=data,
metadata=[metadata for _ in range(number)],
data_type="im")
# Plot before / after transformation
fname_out = str(Path(output, stg_transforms + "slice" + str(i) + ".png"))
logger.debug(f"Fname out: {fname_out}.")
logger.debug(f"\t{dict(metadata)}")
# rescale intensities
if len(stg_transforms[:-1].split("_")) == 1:
before = np.rot90(imed_maths.rescale_values_array(data[0], 0.0, 1.0))
else:
before = after
if isinstance(stack_im[0], torch.Tensor):
after = np.rot90(imed_maths.rescale_values_array(stack_im[0].numpy(), 0.0, 1.0))
else:
after = np.rot90(imed_maths.rescale_values_array(stack_im[0], 0.0, 1.0))
# Plot
imed_utils.plot_transformed_sample(before,
after,
list_title=["\n".join(stg_transforms[:-1].split("_")[:-1]),
"\n".join(stg_transforms[:-1].split("_"))],
fname_out=fname_out,
cmap="jet" if is_mask else "gray")
def run_visualization(input, config, number, output, roi):
"""Utility function to visualize Data Augmentation transformations.
Data augmentation is a key part of the Deep Learning training scheme. This script aims at facilitating the
fine-tuning of data augmentation parameters. To do so, this script provides a step-by-step visualization of the
transformations that are applied on data.
This function applies a series of transformations (defined in a configuration file
``-c``) to ``-n`` 2D slices randomly extracted from an input image (``-i``), and save as png the resulting sample
after each transform.
For example::
ivadomed_visualize_transforms -i t2s.nii.gz -n 1 -c config.json -r t2s_seg.nii.gz
Provides a visualization of a series of three transformation on a randomly selected slice:
.. image:: ../../images/transforms_im.png
:width: 600px
:align: center
And on a binary mask::
ivadomed_visualize_transforms -i t2s_gmseg.nii.gz -n 1 -c config.json -r t2s_seg.nii.gz
Gives:
.. image:: ../../images/transforms_gt.png
:width: 600px
:align: center
Args:
input (string): Image filename. Flag: ``--input``, ``-i``
config (string): Configuration file filename. Flag: ``--config``, ``-c``
number (int): Number of slices randomly extracted. Flag: ``--number``, ``-n``
output (string): Folder path where the results are saved. Flag: ``--ofolder``, ``-o``
roi (string): Filename of the region of interest. Only needed if ROICrop is part of the transformations.
Flag: ``--roi``, ``-r``
"""
# Load context
with open(config, "r") as fhandle:
context = json.load(fhandle)
# Create output folder
if not os.path.isdir(output):
os.makedirs(output)
# Slice extracted according to below axis
axis = imed_utils.AXIS_DCT[context["loader_parameters"]["slice_axis"]]
# Get data
input_img, input_data = get_data(input, axis)
# Image or Mask
is_mask = np.array_equal(input_data, input_data.astype(bool))
# Get zooms
zooms = imed_loader_utils.orient_shapes_hwd(input_img.header.get_zooms(),
slice_axis=axis)
# Get indexes
indexes = random.sample(range(0, input_data.shape[2]), number)
# Get training transforms
training_transforms, _, _ = imed_transforms.get_subdatasets_transforms(
context["transformation"])
if "ROICrop" in training_transforms:
if roi and os.path.isfile(roi):
roi_img, roi_data = get_data(roi, axis)
else:
print(
"\nPlease provide ROI image (-r) in order to apply ROICrop transformation."
)
exit()
# Compose transforms
dict_transforms = {}
stg_transforms = ""
for transform_name in training_transforms:
# We skip NumpyToTensor transform since that s only a change of data type
if transform_name == "NumpyToTensor":
continue
# Update stg_transforms
stg_transforms += transform_name + "_"
# Add new transform to Compose
dict_transforms.update(
{transform_name: training_transforms[transform_name]})
composed_transforms = imed_transforms.Compose(dict_transforms)
# Loop across slices
for i in indexes:
data = [input_data[:, :, i]]
# Init metadata
metadata = imed_loader_utils.SampleMetadata({
"zooms":
zooms,
"data_type":
"gt" if is_mask else "im"
})
# Apply transformations to ROI
if "CenterCrop" in training_transforms or (
"ROICrop" in training_transforms and os.path.isfile(roi)):
metadata.__setitem__('crop_params', {})
# Apply transformations to image
stack_im, _ = composed_transforms(
sample=data,
metadata=[metadata for _ in range(number)],
data_type="im")
# Plot before / after transformation
fname_out = os.path.join(
output, stg_transforms + "slice" + str(i) + ".png")
print("Fname out: {}.".format(fname_out))
print("\t{}".format(dict(metadata)))
# rescale intensities
if len(stg_transforms[:-1].split("_")) == 1:
before = np.rot90(
imed_maths.rescale_values_array(data[0], 0.0, 1.0))
else:
before = after
after = np.rot90(
imed_maths.rescale_values_array(stack_im[0], 0.0, 1.0))
# Plot
imed_utils.plot_transformed_sample(
before,
after,
list_title=[
"\n".join(stg_transforms[:-1].split("_")[:-1]),
"\n".join(stg_transforms[:-1].split("_"))
],
fname_out=fname_out,
cmap="jet" if is_mask else "gray")
def create_test_image(width,
height,
depth=0,
num_contrasts=1,
noise_max=10.0,
num_objs=1,
rad_max=30,
num_seg_classes=1,
random_position=False):
"""Create test image.
Create test image and its segmentation with a given number of objects, classes, and maximum radius.
Compatible with both 2D (depth=0) and 3D images.
Args:
height (int): height image
width (int): width image
depth (int): depth image, if 0 then 2D images are returned
num_contrasts (int): number of contrasts
noise_max (float): noise from the uniform distribution [0,noise_max)
num_objs (int): number of objects
rad_max (int): maximum radius of objects
num_seg_classes (int): number of classes
random_position (bool): If false, the object is located at the center of the image. Otherwise, randomly located.
Return:
list, list: image and segmentation, list of num_contrasts elements of shape (height, width, depth).
Adapted from: https://github.com/Project-MONAI/MONAI/blob/master/monai/data/synthetic.py#L17
"""
assert num_contrasts >= 1
depth_ = depth if depth >= 1 else 2 * rad_max + 1
assert (height > 2 * rad_max) and (width > 2 * rad_max) and (depth_ >
2 * rad_max)
image = np.zeros((height, width, depth_))
for i in range(num_objs):
if random_position:
x = np.random.randint(rad_max, height - rad_max)
y = np.random.randint(rad_max, width - rad_max)
z = np.random.randint(rad_max, depth_ - rad_max)
else:
x, y, z = np.rint(height / 2), np.rint(width / 2), np.rint(depth_ /
2)
rad = np.random.randint(5, rad_max)
spy, spx, spz = np.ogrid[-x:height - x, -y:width - y, -z:depth_ - z]
sphere = (spx * spx + spy * spy + spz * spz) <= rad * rad * rad
if num_seg_classes > 1:
image[sphere] = np.ceil(np.random.random() * num_seg_classes)
else:
image[sphere] = np.random.random() * 0.5 + 0.5
seg = np.ceil(image).astype(np.int32)
if depth == 0:
_, _, z_slice = center_of_mass(seg.astype(np.int))
z_slice = int(round(z_slice))
seg = seg[:, :, z_slice]
list_im, list_seg = [], []
for _ in range(num_contrasts):
norm = np.random.uniform(0,
num_seg_classes * noise_max,
size=image.shape)
noisy_image = imed_maths.rescale_values_array(np.maximum(image, norm))
if depth == 0:
noisy_image = noisy_image[:, :, z_slice]
list_im.append(noisy_image)
list_seg.append(seg)
return list_im, list_seg