def run_test(batch_size, img_name, seg_name, output_dir, device="cuda:0"):
ds = NiftiDataset([img_name], [seg_name], transform=AddChannel(), seg_transform=AddChannel(), image_only=False)
loader = DataLoader(ds, batch_size=1, pin_memory=torch.cuda.is_available())
net = UNet(
dimensions=3, in_channels=1, out_channels=1, channels=(4, 8, 16, 32), strides=(2, 2, 2), num_res_units=2
).to(device)
roi_size = (16, 32, 48)
sw_batch_size = batch_size
def _sliding_window_processor(_engine, batch):
net.eval()
img, seg, meta_data = batch
with torch.no_grad():
seg_probs = sliding_window_inference(img.to(device), roi_size, sw_batch_size, net, device=device)
return predict_segmentation(seg_probs)
infer_engine = Engine(_sliding_window_processor)
SegmentationSaver(
output_dir=output_dir, output_ext=".nii.gz", output_postfix="seg", batch_transform=lambda x: x[2]
).attach(infer_engine)
infer_engine.run(loader)
basename = os.path.basename(img_name)[: -len(".nii.gz")]
saved_name = os.path.join(output_dir, basename, f"{basename}_seg.nii.gz")
return saved_name
def initialize(self, args):
"""
`initialize` is called only once when the model is being loaded.
Implementing `initialize` function is optional. This function allows
the model to intialize any state associated with this model.
"""
# Pull model from google drive
extract_dir = "/models/mednist_class/1"
tar_save_path = os.path.join(extract_dir, model_filename)
download_and_extract(gdrive_url,
tar_save_path,
output_dir=extract_dir,
hash_val=md5_check,
hash_type="md5")
# load model configuration
self.model_config = json.loads(args['model_config'])
# create inferer engine and load PyTorch model
inference_device_kind = args.get('model_instance_kind', None)
logger.info(f"Inference device: {inference_device_kind}")
self.inference_device = torch.device('cpu')
if inference_device_kind is None or inference_device_kind == 'CPU':
self.inference_device = torch.device('cpu')
elif inference_device_kind == 'GPU':
inference_device_id = args.get('model_instance_device_id', '0')
logger.info(f"Inference device id: {inference_device_id}")
if torch.cuda.is_available():
self.inference_device = torch.device(
f'cuda:{inference_device_id}')
cudnn.enabled = True
else:
logger.error(
f"No CUDA device detected. Using device: {inference_device_kind}"
)
# create pre-transforms for MedNIST
self.pre_transforms = Compose([
LoadImage(reader="PILReader", image_only=True, dtype=np.float32),
ScaleIntensity(),
AddChannel(),
AddChannel(),
ToTensor(),
Lambda(func=lambda x: x.to(device=self.inference_device)),
])
# create post-transforms
self.post_transforms = Compose([
Lambda(func=lambda x: x.to(device="cpu")),
])
self.inferer = SimpleInferer()
self.model = torch.jit.load(
f'{pathlib.Path(os.path.realpath(__file__)).parent}{os.path.sep}model.pt',
map_location=self.inference_device)
def main():
config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
tempdir = tempfile.mkdtemp()
print('generating synthetic data to {} (this may take a while)'.format(tempdir))
for i in range(5):
im, seg = create_test_image_3d(128, 128, 128, num_seg_classes=1)
n = nib.Nifti1Image(im, np.eye(4))
nib.save(n, os.path.join(tempdir, 'im%i.nii.gz' % i))
n = nib.Nifti1Image(seg, np.eye(4))
nib.save(n, os.path.join(tempdir, 'seg%i.nii.gz' % i))
images = sorted(glob(os.path.join(tempdir, 'im*.nii.gz')))
segs = sorted(glob(os.path.join(tempdir, 'seg*.nii.gz')))
# define transforms for image and segmentation
imtrans = Compose([ScaleIntensity(), AddChannel(), ToTensor()])
segtrans = Compose([AddChannel(), ToTensor()])
val_ds = NiftiDataset(images, segs, transform=imtrans, seg_transform=segtrans, image_only=False)
# sliding window inference for one image at every iteration
val_loader = DataLoader(val_ds, batch_size=1, num_workers=1, pin_memory=torch.cuda.is_available())
device = torch.device('cuda:0')
model = UNet(
dimensions=3,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
).to(device)
model.load_state_dict(torch.load('best_metric_model.pth'))
model.eval()
with torch.no_grad():
metric_sum = 0.
metric_count = 0
saver = NiftiSaver(output_dir='./output')
for val_data in val_loader:
val_images, val_labels = val_data[0].to(device), val_data[1].to(device)
# define sliding window size and batch size for windows inference
roi_size = (96, 96, 96)
sw_batch_size = 4
val_outputs = sliding_window_inference(val_images, roi_size, sw_batch_size, model)
value = compute_meandice(y_pred=val_outputs, y=val_labels, include_background=True,
to_onehot_y=False, add_sigmoid=True)
metric_count += len(value)
metric_sum += value.sum().item()
val_outputs = (val_outputs.sigmoid() >= 0.5).float()
saver.save_batch(val_outputs, val_data[2])
metric = metric_sum / metric_count
print('evaluation metric:', metric)
shutil.rmtree(tempdir)
def main(tempdir):
config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
print(f"generating synthetic data to {tempdir} (this may take a while)")
for i in range(5):
im, seg = create_test_image_3d(128, 128, 128, num_seg_classes=1)
n = nib.Nifti1Image(im, np.eye(4))
nib.save(n, os.path.join(tempdir, f"im{i:d}.nii.gz"))
n = nib.Nifti1Image(seg, np.eye(4))
nib.save(n, os.path.join(tempdir, f"seg{i:d}.nii.gz"))
images = sorted(glob(os.path.join(tempdir, "im*.nii.gz")))
segs = sorted(glob(os.path.join(tempdir, "seg*.nii.gz")))
# define transforms for image and segmentation
imtrans = Compose([ScaleIntensity(), AddChannel(), ToTensor()])
segtrans = Compose([AddChannel(), ToTensor()])
val_ds = ImageDataset(images, segs, transform=imtrans, seg_transform=segtrans, image_only=False)
# sliding window inference for one image at every iteration
val_loader = DataLoader(val_ds, batch_size=1, num_workers=1, pin_memory=torch.cuda.is_available())
dice_metric = DiceMetric(include_background=True, reduction="mean")
post_trans = Compose([Activations(sigmoid=True), AsDiscrete(threshold_values=True)])
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = UNet(
dimensions=3,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
).to(device)
model.load_state_dict(torch.load("best_metric_model_segmentation3d_array.pth"))
model.eval()
with torch.no_grad():
metric_sum = 0.0
metric_count = 0
saver = NiftiSaver(output_dir="./output")
for val_data in val_loader:
val_images, val_labels = val_data[0].to(device), val_data[1].to(device)
# define sliding window size and batch size for windows inference
roi_size = (96, 96, 96)
sw_batch_size = 4
val_outputs = sliding_window_inference(val_images, roi_size, sw_batch_size, model)
val_outputs = post_trans(val_outputs)
value, _ = dice_metric(y_pred=val_outputs, y=val_labels)
metric_count += len(value)
metric_sum += value.item() * len(value)
saver.save_batch(val_outputs, val_data[2])
metric = metric_sum / metric_count
print("evaluation metric:", metric)
def main(tempdir):
config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
print(f"generating synthetic data to {tempdir} (this may take a while)")
for i in range(5):
im, seg = create_test_image_2d(128, 128, num_seg_classes=1)
Image.fromarray((im * 255).astype("uint8")).save(os.path.join(tempdir, f"img{i:d}.png"))
Image.fromarray((seg * 255).astype("uint8")).save(os.path.join(tempdir, f"seg{i:d}.png"))
images = sorted(glob(os.path.join(tempdir, "img*.png")))
segs = sorted(glob(os.path.join(tempdir, "seg*.png")))
# define transforms for image and segmentation
imtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity(), EnsureType()])
segtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity(), EnsureType()])
val_ds = ArrayDataset(images, imtrans, segs, segtrans)
# sliding window inference for one image at every iteration
val_loader = DataLoader(val_ds, batch_size=1, num_workers=1, pin_memory=torch.cuda.is_available())
dice_metric = DiceMetric(include_background=True, reduction="mean", get_not_nans=False)
post_trans = Compose([EnsureType(), Activations(sigmoid=True), AsDiscrete(threshold=0.5)])
saver = SaveImage(output_dir="./output", output_ext=".png", output_postfix="seg")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = UNet(
spatial_dims=2,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
).to(device)
model.load_state_dict(torch.load("best_metric_model_segmentation2d_array.pth"))
model.eval()
with torch.no_grad():
for val_data in val_loader:
val_images, val_labels = val_data[0].to(device), val_data[1].to(device)
# define sliding window size and batch size for windows inference
roi_size = (96, 96)
sw_batch_size = 4
val_outputs = sliding_window_inference(val_images, roi_size, sw_batch_size, model)
val_outputs = [post_trans(i) for i in decollate_batch(val_outputs)]
val_labels = decollate_batch(val_labels)
# compute metric for current iteration
dice_metric(y_pred=val_outputs, y=val_labels)
for val_output in val_outputs:
saver(val_output)
# aggregate the final mean dice result
print("evaluation metric:", dice_metric.aggregate().item())
# reset the status
dice_metric.reset()
def _define_prediction_transforms(self):
"""Define and initialize all prediction data transforms.
* prediction set images transform
* prediction set images post-transform
@return True if data transforms could be instantiated, False otherwise.
"""
# Define transforms for prediction
self._prediction_image_transforms = Compose(
[
LoadImage(image_only=True),
ScaleIntensity(),
AddChannel(),
ToTensor(),
]
)
self._prediction_post_transforms = Compose(
[
Activations(softmax=True),
AsDiscrete(threshold_values=True),
]
)
def test_inverse_array(self, use_compose, dtype, device):
img: MetaTensor
tr = Compose([
AddChannel(),
Orientation("RAS"),
Flip(1),
Spacing([1.0, 1.2, 0.9], align_corners=False)
])
num_invertible = len(
[i for i in tr.transforms if isinstance(i, InvertibleTransform)])
# forward
img = tr(self.get_image(dtype, device))
self.assertEqual(len(img.applied_operations), num_invertible)
# inverse with Compose
if use_compose:
img = tr.inverse(img)
self.assertEqual(len(img.applied_operations), 0)
# inverse individually
else:
_tr: InvertibleTransform
num_to_inverse = num_invertible
for _tr in tr.transforms[::-1]:
if isinstance(_tr, InvertibleTransform):
img = _tr.inverse(img)
num_to_inverse -= 1
self.assertEqual(len(img.applied_operations),
num_to_inverse)
def run_inference_test(root_dir, test_x, test_y,
device=torch.device("cuda:0")):
# define transforms for image and classification
val_transforms = Compose(
[LoadPNG(image_only=True),
AddChannel(),
ScaleIntensity(),
ToTensor()])
val_ds = MedNISTDataset(test_x, test_y, val_transforms)
val_loader = DataLoader(val_ds, batch_size=300, num_workers=10)
model = densenet121(
spatial_dims=2,
in_channels=1,
out_channels=len(np.unique(test_y)),
).to(device)
model_filename = os.path.join(root_dir, "best_metric_model.pth")
model.load_state_dict(torch.load(model_filename))
model.eval()
y_true = list()
y_pred = list()
with torch.no_grad():
for test_data in val_loader:
test_images, test_labels = test_data[0].to(
device), test_data[1].to(device)
pred = model(test_images).argmax(dim=1)
for i in range(len(pred)):
y_true.append(test_labels[i].item())
y_pred.append(pred[i].item())
tps = [
np.sum((np.asarray(y_true) == idx) & (np.asarray(y_pred) == idx))
for idx in np.unique(test_y)
]
return tps
def main():
monai.config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
# IXI dataset as a demo, downloadable from https://brain-development.org/ixi-dataset/
images = [
'/workspace/data/medical/ixi/IXI-T1/IXI607-Guys-1097-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI175-HH-1570-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI385-HH-2078-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI344-Guys-0905-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI409-Guys-0960-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI584-Guys-1129-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI253-HH-1694-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI092-HH-1436-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI574-IOP-1156-T1.nii.gz',
'/workspace/data/medical/ixi/IXI-T1/IXI585-Guys-1130-T1.nii.gz'
]
# 2 binary labels for gender classification: man and woman
labels = np.array([
0, 0, 1, 0, 1, 0, 1, 0, 1, 0
])
# Define transforms for image
val_transforms = Compose([
ScaleIntensity(),
AddChannel(),
Resize((96, 96, 96)),
ToTensor()
])
# Define nifti dataset
val_ds = NiftiDataset(image_files=images, labels=labels, transform=val_transforms, image_only=False)
# create a validation data loader
val_loader = DataLoader(val_ds, batch_size=2, num_workers=4, pin_memory=torch.cuda.is_available())
# Create DenseNet121
device = torch.device('cuda:0')
model = monai.networks.nets.densenet.densenet121(
spatial_dims=3,
in_channels=1,
out_channels=2,
).to(device)
model.load_state_dict(torch.load('best_metric_model.pth'))
model.eval()
with torch.no_grad():
num_correct = 0.
metric_count = 0
saver = CSVSaver(output_dir='./output')
for val_data in val_loader:
val_images, val_labels = val_data[0].to(device), val_data[1].to(device)
val_outputs = model(val_images).argmax(dim=1)
value = torch.eq(val_outputs, val_labels)
metric_count += len(value)
num_correct += value.sum().item()
saver.save_batch(val_outputs, val_data[2])
metric = num_correct / metric_count
print('evaluation metric:', metric)
saver.finalize()
def test_epistemic_scoring(self):
input_size = (20, 20, 20)
device = "cuda" if torch.cuda.is_available() else "cpu"
keys = ["image", "label"]
num_training_ims = 10
train_data = self.get_data(num_training_ims, input_size)
test_data = self.get_data(1, input_size)
transforms = Compose([
AddChanneld(keys),
CropForegroundd(keys, source_key="image"),
DivisiblePadd(keys, 4),
])
infer_transforms = Compose([
AddChannel(),
CropForeground(),
DivisiblePad(4),
])
train_ds = CacheDataset(train_data, transforms)
# output might be different size, so pad so that they match
train_loader = DataLoader(train_ds,
batch_size=2,
collate_fn=pad_list_data_collate)
model = UNet(3, 1, 1, channels=(6, 6), strides=(2, 2)).to(device)
loss_function = DiceLoss(sigmoid=True)
optimizer = torch.optim.Adam(model.parameters(), 1e-3)
num_epochs = 10
for _ in trange(num_epochs):
epoch_loss = 0
for batch_data in train_loader:
inputs, labels = batch_data["image"].to(
device), batch_data["label"].to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_loss /= len(train_loader)
entropy_score = EpistemicScoring(model=model,
transforms=infer_transforms,
roi_size=[20, 20, 20],
num_samples=10)
# Call Individual Infer from Epistemic Scoring
ip_stack = [test_data["image"], test_data["image"], test_data["image"]]
ip_stack = np.array(ip_stack)
score_3d = entropy_score.entropy_3d_volume(ip_stack)
score_3d_sum = np.sum(score_3d)
# Call Entropy Metric from Epistemic Scoring
self.assertEqual(score_3d.shape, input_size)
self.assertIsInstance(score_3d_sum, np.float32)
self.assertGreater(score_3d_sum, 3.0)
def test_decollation_list(self, *transforms):
t_compose = Compose([AddChannel(), Compose(transforms), ToTensor()])
# If nibabel present, read from disk
if has_nib:
t_compose = _ListCompose([LoadImage(image_only=False), t_compose])
dataset = Dataset(self.data_list, t_compose)
self.check_decollate(dataset=dataset)
def run_test(batch_size=64, train_steps=200, device=torch.device("cuda:0")):
class _TestBatch(Dataset):
def __init__(self, transforms):
self.transforms = transforms
def __getitem__(self, _unused_id):
im, seg = create_test_image_2d(128,
128,
noise_max=1,
num_objs=4,
num_seg_classes=1)
seed = np.random.randint(2147483647)
self.transforms.set_random_state(seed=seed)
im = self.transforms(im)
self.transforms.set_random_state(seed=seed)
seg = self.transforms(seg)
return im, seg
def __len__(self):
return train_steps
net = UNet(
dimensions=2,
in_channels=1,
out_channels=1,
channels=(4, 8, 16, 32),
strides=(2, 2, 2),
num_res_units=2,
).to(device)
loss = DiceLoss(do_sigmoid=True)
opt = torch.optim.Adam(net.parameters(), 1e-2)
train_transforms = Compose([
AddChannel(),
ScaleIntensity(),
RandSpatialCrop((96, 96), random_size=False),
RandRotate90(),
ToTensor()
])
src = DataLoader(_TestBatch(train_transforms),
batch_size=batch_size,
shuffle=True)
net.train()
epoch_loss = 0
step = 0
for img, seg in src:
step += 1
opt.zero_grad()
output = net(img.to(device))
step_loss = loss(output, seg.to(device))
step_loss.backward()
opt.step()
epoch_loss += step_loss.item()
epoch_loss /= step
return epoch_loss, step
def predict(model,image):
image = AddChannel()(image)
image = ToTensor()(image)
output,_,_,_,_ = model(image)
output = (output > 0.5)
output = output.numpy()
return output
def run_test(batch_size, img_name, seg_name, output_dir, device="cuda:0"):
ds = ImageDataset([img_name], [seg_name],
transform=AddChannel(),
seg_transform=AddChannel(),
image_only=True)
loader = DataLoader(ds, batch_size=1, pin_memory=torch.cuda.is_available())
net = UNet(spatial_dims=3,
in_channels=1,
out_channels=1,
channels=(4, 8, 16, 32),
strides=(2, 2, 2),
num_res_units=2).to(device)
roi_size = (16, 32, 48)
sw_batch_size = batch_size
saver = SaveImage(output_dir=output_dir,
output_ext=".nii.gz",
output_postfix="seg")
def _sliding_window_processor(_engine, batch):
img = batch[0] # first item from ImageDataset is the input image
with eval_mode(net):
seg_probs = sliding_window_inference(img.to(device),
roi_size,
sw_batch_size,
net,
device=device)
return predict_segmentation(seg_probs)
def save_func(engine):
if pytorch_after(1, 9, 1):
for m in engine.state.output:
saver(m)
else:
saver(engine.state.output[0])
infer_engine = Engine(_sliding_window_processor)
infer_engine.add_event_handler(Events.ITERATION_COMPLETED, save_func)
infer_engine.run(loader)
basename = os.path.basename(img_name)[:-len(".nii.gz")]
saved_name = os.path.join(output_dir, basename, f"{basename}_seg.nii.gz")
return saved_name
def test_flatten_and_len(self):
x = AddChannel()
t1 = Compose([x, x, x, x, Compose([Compose([x, x]), x, x])])
t2 = t1.flatten()
for t in t2.transforms:
self.assertNotIsInstance(t, Compose)
# test len
self.assertEqual(len(t1), 8)
def classify_image(image):
# make conversions to image and save temporarily
im = Image.open(image)
im = im.convert(mode='L')
im = im.resize((64, 64))
im.save('conversion.jpeg', 'JPEG')
# Define MONAI transforms, Dataset and Dataloader to process image
val_transforms = Compose([
LoadImage(image_only=True),
AddChannel(),
ScaleIntensity(),
ToTensor()
])
test_ds = MedNISTDataset(['conversion.jpeg'], [0], val_transforms)
test_loader = torch.utils.data.DataLoader(test_ds)
# Define Network
device = torch.device("cpu")
model = densenet121(spatial_dims=2, in_channels=1,
out_channels=num_class).to(device)
# Make prediction
model.load_state_dict(
torch.load(
"SmartEMR_Imaging/MONAI_DATA_DIRECTORY/best_metric_model_cpu.pth"))
model.eval()
y_true = list()
y_pred = list()
with torch.no_grad():
for test_data in test_loader:
test_images, test_labels = (
test_data[0].to(device),
test_data[1].to(device),
)
pred = model(test_images).argmax(dim=1)
for i in range(len(pred)):
y_true.append(test_labels[i].item())
y_pred.append(pred[i].item())
# clean up
os.remove('conversion.jpeg')
return class_tags[y_pred[0]]
def setUp(self):
if not has_nib:
self.skipTest("nibabel required for test_inverse")
set_determinism(seed=0)
self.all_data = {}
affine = make_rand_affine()
affine[0] *= 2
im_1d = AddChannel()(np.arange(0, 10))
self.all_data["1D"] = {"image": im_1d, "label": im_1d, "other": im_1d}
im_2d_fname, seg_2d_fname = [make_nifti_image(i) for i in create_test_image_2d(101, 100)]
im_3d_fname, seg_3d_fname = [make_nifti_image(i, affine) for i in create_test_image_3d(100, 101, 107)]
load_ims = Compose([LoadImaged(KEYS), AddChanneld(KEYS)])
self.all_data["2D"] = load_ims({"image": im_2d_fname, "label": seg_2d_fname})
self.all_data["3D"] = load_ims({"image": im_3d_fname, "label": seg_3d_fname})
def predict_mask(model, images):
image_array = []
for image in images:
image_array.append(image.pixel_array)
image_array = np.expand_dims(
np.transpose(np.array(image_array).astype('float32')), (0, 1))
data_transforms = Compose([AddChannel(), NormalizeIntensity(), ToTensor()])
dataset = monai.data.Dataset(data=image_array, transform=data_transforms)
print(dataset[0].shape)
test_mask = sliding_window_inference(dataset[0],
roi_size=[128, 128, 16],
sw_batch_size=1,
predictor=model)
test_mask = test_mask.argmax(1).detach().cpu().numpy()
test_mask = np.transpose(np.squeeze(test_mask, 0))
test_mask = test_mask.astype('uint8')
test_mask = np.asarray(test_mask, order='C')
return test_mask
def main(tempdir):
config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
print(f"generating synthetic data to {tempdir} (this may take a while)")
for i in range(5):
im, seg = create_test_image_3d(128, 128, 128, num_seg_classes=1)
n = nib.Nifti1Image(im, np.eye(4))
nib.save(n, os.path.join(tempdir, f"im{i:d}.nii.gz"))
n = nib.Nifti1Image(seg, np.eye(4))
nib.save(n, os.path.join(tempdir, f"seg{i:d}.nii.gz"))
images = sorted(glob(os.path.join(tempdir, "im*.nii.gz")))
segs = sorted(glob(os.path.join(tempdir, "seg*.nii.gz")))
# define transforms for image and segmentation
imtrans = Compose([ScaleIntensity(), AddChannel(), ToTensor()])
segtrans = Compose([AddChannel(), ToTensor()])
ds = ImageDataset(images,
segs,
transform=imtrans,
seg_transform=segtrans,
image_only=False)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net = UNet(
dimensions=3,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
).to(device)
# define sliding window size and batch size for windows inference
roi_size = (96, 96, 96)
sw_batch_size = 4
post_trans = Compose(
[Activations(sigmoid=True),
AsDiscrete(threshold_values=True)])
def _sliding_window_processor(engine, batch):
net.eval()
with torch.no_grad():
val_images, val_labels = batch[0].to(device), batch[1].to(device)
seg_probs = sliding_window_inference(val_images, roi_size,
sw_batch_size, net)
seg_probs = post_trans(seg_probs)
return seg_probs, val_labels
evaluator = Engine(_sliding_window_processor)
# add evaluation metric to the evaluator engine
MeanDice().attach(evaluator, "Mean_Dice")
# StatsHandler prints loss at every iteration and print metrics at every epoch,
# we don't need to print loss for evaluator, so just print metrics, user can also customize print functions
val_stats_handler = StatsHandler(
name="evaluator",
output_transform=lambda x:
None, # no need to print loss value, so disable per iteration output
)
val_stats_handler.attach(evaluator)
# for the array data format, assume the 3rd item of batch data is the meta_data
file_saver = SegmentationSaver(
output_dir="tempdir",
output_ext=".nii.gz",
output_postfix="seg",
name="evaluator",
batch_transform=lambda x: x[2],
output_transform=lambda output: output[0],
)
file_saver.attach(evaluator)
# the model was trained by "unet_training_array" example
ckpt_saver = CheckpointLoader(
load_path="./runs_array/net_checkpoint_100.pt", load_dict={"net": net})
ckpt_saver.attach(evaluator)
# sliding window inference for one image at every iteration
loader = DataLoader(ds,
batch_size=1,
num_workers=1,
pin_memory=torch.cuda.is_available())
state = evaluator.run(loader)
print(state)
def main():
monai.config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
# IXI dataset as a demo, downloadable from https://brain-development.org/ixi-dataset/
# the path of ixi IXI-T1 dataset
data_path = os.sep.join(
[".", "workspace", "data", "medical", "ixi", "IXI-T1"])
images = [
"IXI607-Guys-1097-T1.nii.gz",
"IXI175-HH-1570-T1.nii.gz",
"IXI385-HH-2078-T1.nii.gz",
"IXI344-Guys-0905-T1.nii.gz",
"IXI409-Guys-0960-T1.nii.gz",
"IXI584-Guys-1129-T1.nii.gz",
"IXI253-HH-1694-T1.nii.gz",
"IXI092-HH-1436-T1.nii.gz",
"IXI574-IOP-1156-T1.nii.gz",
"IXI585-Guys-1130-T1.nii.gz",
]
images = [os.sep.join([data_path, f]) for f in images]
# 2 binary labels for gender classification: man and woman
labels = np.array([0, 0, 1, 0, 1, 0, 1, 0, 1, 0], dtype=np.int64)
# Define transforms for image
val_transforms = Compose(
[ScaleIntensity(),
AddChannel(),
Resize((96, 96, 96)),
EnsureType()])
# Define image dataset
val_ds = ImageDataset(image_files=images,
labels=labels,
transform=val_transforms,
image_only=False)
# create a validation data loader
val_loader = DataLoader(val_ds,
batch_size=2,
num_workers=4,
pin_memory=torch.cuda.is_available())
# Create DenseNet121
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = monai.networks.nets.DenseNet121(spatial_dims=3,
in_channels=1,
out_channels=2).to(device)
model.load_state_dict(
torch.load("best_metric_model_classification3d_array.pth"))
model.eval()
with torch.no_grad():
num_correct = 0.0
metric_count = 0
saver = CSVSaver(output_dir="./output")
for val_data in val_loader:
val_images, val_labels = val_data[0].to(device), val_data[1].to(
device)
val_outputs = model(val_images).argmax(dim=1)
value = torch.eq(val_outputs, val_labels)
metric_count += len(value)
num_correct += value.sum().item()
saver.save_batch(val_outputs, val_data[2])
metric = num_correct / metric_count
print("evaluation metric:", metric)
saver.finalize()
def main(tempdir):
monai.config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
# create a temporary directory and 40 random image, mask pairs
print(f"generating synthetic data to {tempdir} (this may take a while)")
for i in range(40):
im, seg = create_test_image_2d(128, 128, num_seg_classes=1)
Image.fromarray(im.astype("uint8")).save(
os.path.join(tempdir, f"img{i:d}.png"))
Image.fromarray(seg.astype("uint8")).save(
os.path.join(tempdir, f"seg{i:d}.png"))
images = sorted(glob(os.path.join(tempdir, "img*.png")))
segs = sorted(glob(os.path.join(tempdir, "seg*.png")))
train_files = [{
"img": img,
"seg": seg
} for img, seg in zip(images[:20], segs[:20])]
val_files = [{
"img": img,
"seg": seg
} for img, seg in zip(images[-20:], segs[-20:])]
# define transforms for image and segmentation
train_imtrans = Compose([
LoadImage(image_only=True),
ScaleIntensity(),
AddChannel(),
RandSpatialCrop((96, 96), random_size=False),
RandRotate90(prob=0.5, spatial_axes=(0, 1)),
ToTensor(),
])
train_segtrans = Compose([
LoadImage(image_only=True),
AddChannel(),
RandSpatialCrop((96, 96), random_size=False),
RandRotate90(prob=0.5, spatial_axes=(0, 1)),
ToTensor(),
])
val_imtrans = Compose([
LoadImage(image_only=True),
ScaleIntensity(),
AddChannel(),
ToTensor()
])
val_segtrans = Compose(
[LoadImage(image_only=True),
AddChannel(), ToTensor()])
# define array dataset, data loader
check_ds = ArrayDataset(images, train_imtrans, segs, train_segtrans)
check_loader = DataLoader(check_ds,
batch_size=10,
num_workers=2,
pin_memory=torch.cuda.is_available())
im, seg = monai.utils.misc.first(check_loader)
print(im.shape, seg.shape)
# create a training data loader
train_ds = ArrayDataset(images[:20], train_imtrans, segs[:20],
train_segtrans)
train_loader = DataLoader(train_ds,
batch_size=4,
shuffle=True,
num_workers=8,
pin_memory=torch.cuda.is_available())
# create a validation data loader
val_ds = ArrayDataset(images[-20:], val_imtrans, segs[-20:], val_segtrans)
val_loader = DataLoader(val_ds,
batch_size=1,
num_workers=4,
pin_memory=torch.cuda.is_available())
dice_metric = DiceMetric(include_background=True, reduction="mean")
post_trans = Compose(
[Activations(sigmoid=True),
AsDiscrete(threshold_values=True)])
# create UNet, DiceLoss and Adam optimizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = monai.networks.nets.UNet(
dimensions=2,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
).to(device)
loss_function = monai.losses.DiceLoss(sigmoid=True)
optimizer = torch.optim.Adam(model.parameters(), 1e-3)
# start a typical PyTorch training
val_interval = 2
best_metric = -1
best_metric_epoch = -1
epoch_loss_values = list()
metric_values = list()
writer = SummaryWriter()
for epoch in range(10):
print("-" * 10)
print(f"epoch {epoch + 1}/{10}")
model.train()
epoch_loss = 0
step = 0
for batch_data in train_loader:
step += 1
inputs, labels = batch_data[0].to(device), batch_data[1].to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_len = len(train_ds) // train_loader.batch_size
print(f"{step}/{epoch_len}, train_loss: {loss.item():.4f}")
writer.add_scalar("train_loss", loss.item(),
epoch_len * epoch + step)
epoch_loss /= step
epoch_loss_values.append(epoch_loss)
print(f"epoch {epoch + 1} average loss: {epoch_loss:.4f}")
if (epoch + 1) % val_interval == 0:
model.eval()
with torch.no_grad():
metric_sum = 0.0
metric_count = 0
val_images = None
val_labels = None
val_outputs = None
for val_data in val_loader:
val_images, val_labels = val_data[0].to(
device), val_data[1].to(device)
roi_size = (96, 96)
sw_batch_size = 4
val_outputs = sliding_window_inference(
val_images, roi_size, sw_batch_size, model)
val_outputs = post_trans(val_outputs)
value, _ = dice_metric(y_pred=val_outputs, y=val_labels)
metric_count += len(value)
metric_sum += value.item() * len(value)
metric = metric_sum / metric_count
metric_values.append(metric)
if metric > best_metric:
best_metric = metric
best_metric_epoch = epoch + 1
torch.save(model.state_dict(),
"best_metric_model_segmentation2d_array.pth")
print("saved new best metric model")
print(
"current epoch: {} current mean dice: {:.4f} best mean dice: {:.4f} at epoch {}"
.format(epoch + 1, metric, best_metric, best_metric_epoch))
writer.add_scalar("val_mean_dice", metric, epoch + 1)
# plot the last model output as GIF image in TensorBoard with the corresponding image and label
plot_2d_or_3d_image(val_images,
epoch + 1,
writer,
index=0,
tag="image")
plot_2d_or_3d_image(val_labels,
epoch + 1,
writer,
index=0,
tag="label")
plot_2d_or_3d_image(val_outputs,
epoch + 1,
writer,
index=0,
tag="output")
print(
f"train completed, best_metric: {best_metric:.4f} at epoch: {best_metric_epoch}"
)
writer.close()
def test_err_msg(self):
transforms = Compose([abs, AddChannel(), round], log_stats=False)
with self.assertRaisesRegex(Exception, "AddChannel"):
transforms(42.1)
import os
import shutil
import tempfile
import unittest
import nibabel as nib
import numpy as np
from parameterized import parameterized
from monai.data import ArrayDataset
from monai.transforms import AddChannel, Compose, LoadNifti, RandAdjustContrast, Spacing, RandGaussianNoise
TEST_CASE_1 = [
Compose([
LoadNifti(image_only=True),
AddChannel(),
RandGaussianNoise(prob=1.0)
]),
Compose([
LoadNifti(image_only=True),
AddChannel(),
RandGaussianNoise(prob=1.0)
]),
(0, 1),
(1, 128, 128, 128),
]
TEST_CASE_2 = [
Compose([
LoadNifti(image_only=True),
AddChannel(),
import os
import shutil
import tempfile
import unittest
import nibabel as nib
import numpy as np
from parameterized import parameterized
from torch.utils.data import DataLoader
from monai.data import ArrayDataset
from monai.transforms import AddChannel, Compose, LoadNifti, RandAdjustContrast, RandGaussianNoise, Spacing
TEST_CASE_1 = [
Compose([LoadNifti(image_only=True), AddChannel(), RandGaussianNoise(prob=1.0)]),
Compose([LoadNifti(image_only=True), AddChannel(), RandGaussianNoise(prob=1.0)]),
(0, 1),
(1, 128, 128, 128),
]
TEST_CASE_2 = [
Compose([LoadNifti(image_only=True), AddChannel(), RandAdjustContrast(prob=1.0)]),
Compose([LoadNifti(image_only=True), AddChannel(), RandAdjustContrast(prob=1.0)]),
(0, 1),
(1, 128, 128, 128),
]
class TestCompose(Compose):
def __call__(self, input_):
def run_training_test(root_dir,
train_x,
train_y,
val_x,
val_y,
device="cuda:0",
num_workers=10):
monai.config.print_config()
# define transforms for image and classification
train_transforms = Compose([
LoadPNG(image_only=True),
AddChannel(),
ScaleIntensity(),
RandRotate(range_x=np.pi / 12, prob=0.5, keep_size=True),
RandFlip(spatial_axis=0, prob=0.5),
RandZoom(min_zoom=0.9, max_zoom=1.1, prob=0.5),
ToTensor(),
])
train_transforms.set_random_state(1234)
val_transforms = Compose(
[LoadPNG(image_only=True),
AddChannel(),
ScaleIntensity(),
ToTensor()])
# create train, val data loaders
train_ds = MedNISTDataset(train_x, train_y, train_transforms)
train_loader = DataLoader(train_ds,
batch_size=300,
shuffle=True,
num_workers=num_workers)
val_ds = MedNISTDataset(val_x, val_y, val_transforms)
val_loader = DataLoader(val_ds, batch_size=300, num_workers=num_workers)
model = densenet121(spatial_dims=2,
in_channels=1,
out_channels=len(np.unique(train_y))).to(device)
loss_function = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), 1e-5)
epoch_num = 4
val_interval = 1
# start training validation
best_metric = -1
best_metric_epoch = -1
epoch_loss_values = list()
metric_values = list()
model_filename = os.path.join(root_dir, "best_metric_model.pth")
for epoch in range(epoch_num):
print("-" * 10)
print(f"Epoch {epoch + 1}/{epoch_num}")
model.train()
epoch_loss = 0
step = 0
for batch_data in train_loader:
step += 1
inputs, labels = batch_data[0].to(device), batch_data[1].to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_loss /= step
epoch_loss_values.append(epoch_loss)
print(f"epoch {epoch + 1} average loss:{epoch_loss:0.4f}")
if (epoch + 1) % val_interval == 0:
model.eval()
with torch.no_grad():
y_pred = torch.tensor([], dtype=torch.float32, device=device)
y = torch.tensor([], dtype=torch.long, device=device)
for val_data in val_loader:
val_images, val_labels = val_data[0].to(
device), val_data[1].to(device)
y_pred = torch.cat([y_pred, model(val_images)], dim=0)
y = torch.cat([y, val_labels], dim=0)
auc_metric = compute_roc_auc(y_pred,
y,
to_onehot_y=True,
softmax=True)
metric_values.append(auc_metric)
acc_value = torch.eq(y_pred.argmax(dim=1), y)
acc_metric = acc_value.sum().item() / len(acc_value)
if auc_metric > best_metric:
best_metric = auc_metric
best_metric_epoch = epoch + 1
torch.save(model.state_dict(), model_filename)
print("saved new best metric model")
print(
f"current epoch {epoch +1} current AUC: {auc_metric:0.4f} "
f"current accuracy: {acc_metric:0.4f} best AUC: {best_metric:0.4f} at epoch {best_metric_epoch}"
)
print(
f"train completed, best_metric: {best_metric:0.4f} at epoch: {best_metric_epoch}"
)
return epoch_loss_values, best_metric, best_metric_epoch
def main():
config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
tempdir = tempfile.mkdtemp()
print('generating synthetic data to {} (this may take a while)'.format(tempdir))
for i in range(5):
im, seg = create_test_image_3d(128, 128, 128, num_seg_classes=1)
n = nib.Nifti1Image(im, np.eye(4))
nib.save(n, os.path.join(tempdir, 'im%i.nii.gz' % i))
n = nib.Nifti1Image(seg, np.eye(4))
nib.save(n, os.path.join(tempdir, 'seg%i.nii.gz' % i))
images = sorted(glob(os.path.join(tempdir, 'im*.nii.gz')))
segs = sorted(glob(os.path.join(tempdir, 'seg*.nii.gz')))
# define transforms for image and segmentation
imtrans = Compose([ScaleIntensity(), AddChannel(), ToTensor()])
segtrans = Compose([AddChannel(), ToTensor()])
ds = NiftiDataset(images, segs, transform=imtrans, seg_transform=segtrans, image_only=False)
device = torch.device('cuda:0')
net = UNet(
dimensions=3,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
)
net.to(device)
# define sliding window size and batch size for windows inference
roi_size = (96, 96, 96)
sw_batch_size = 4
def _sliding_window_processor(engine, batch):
net.eval()
with torch.no_grad():
val_images, val_labels = batch[0].to(device), batch[1].to(device)
seg_probs = sliding_window_inference(val_images, roi_size, sw_batch_size, net)
return seg_probs, val_labels
evaluator = Engine(_sliding_window_processor)
# add evaluation metric to the evaluator engine
MeanDice(add_sigmoid=True, to_onehot_y=False).attach(evaluator, 'Mean_Dice')
# StatsHandler prints loss at every iteration and print metrics at every epoch,
# we don't need to print loss for evaluator, so just print metrics, user can also customize print functions
val_stats_handler = StatsHandler(
name='evaluator',
output_transform=lambda x: None # no need to print loss value, so disable per iteration output
)
val_stats_handler.attach(evaluator)
# for the array data format, assume the 3rd item of batch data is the meta_data
file_saver = SegmentationSaver(
output_dir='tempdir', output_ext='.nii.gz', output_postfix='seg', name='evaluator',
batch_transform=lambda x: x[2], output_transform=lambda output: predict_segmentation(output[0]))
file_saver.attach(evaluator)
# the model was trained by "unet_training_array" example
ckpt_saver = CheckpointLoader(load_path='./runs/net_checkpoint_50.pth', load_dict={'net': net})
ckpt_saver.attach(evaluator)
# sliding window inference for one image at every iteration
loader = DataLoader(ds, batch_size=1, num_workers=1, pin_memory=torch.cuda.is_available())
state = evaluator.run(loader)
shutil.rmtree(tempdir)
def _define_training_transforms(self):
"""Define and initialize all training data transforms.
* training set images transform
* training set masks transform
* validation set images transform
* validation set masks transform
* validation set images post-transform
* test set images transform
* test set masks transform
* test set images post-transform
* prediction set images transform
* prediction set images post-transform
@return True if data transforms could be instantiated, False otherwise.
"""
if self._mask_type == MaskType.UNKNOWN:
raise Exception("The mask type is unknown. Cannot continue!")
# Depending on the mask type, we will need to adapt the Mask Loader
# and Transform. We start by initializing the most common types.
MaskLoader = LoadMask(self._mask_type)
MaskTransform = Identity
# Adapt the transform for the LABEL types
if self._mask_type == MaskType.TIFF_LABELS or self._mask_type == MaskType.NUMPY_LABELS:
MaskTransform = ToOneHot(num_classes=self._out_channels)
# The H5_ONE_HOT type requires a different loader
if self._mask_type == MaskType.H5_ONE_HOT:
# MaskLoader: still missing
raise Exception("HDF5 one-hot masks are not supported yet!")
# Define transforms for training
self._train_image_transforms = Compose(
[
LoadImage(image_only=True),
ScaleIntensity(),
AddChannel(),
RandSpatialCrop(self._roi_size, random_size=False),
RandRotate90(prob=0.5, spatial_axes=(0, 1)),
ToTensor()
]
)
self._train_mask_transforms = Compose(
[
MaskLoader,
MaskTransform,
RandSpatialCrop(self._roi_size, random_size=False),
RandRotate90(prob=0.5, spatial_axes=(0, 1)),
ToTensor()
]
)
# Define transforms for validation
self._validation_image_transforms = Compose(
[
LoadImage(image_only=True),
ScaleIntensity(),
AddChannel(),
ToTensor()
]
)
self._validation_mask_transforms = Compose(
[
MaskLoader,
MaskTransform,
ToTensor()
]
)
# Define transforms for testing
self._test_image_transforms = Compose(
[
LoadImage(image_only=True),
ScaleIntensity(),
AddChannel(),
ToTensor()
]
)
self._test_mask_transforms = Compose(
[
MaskLoader,
MaskTransform,
ToTensor()
]
)
# Post transforms
self._validation_post_transforms = Compose(
[
Activations(softmax=True),
AsDiscrete(threshold_values=True)
]
)
self._test_post_transforms = Compose(
[
Activations(softmax=True),
AsDiscrete(threshold_values=True)
]
)
print(
'generating synthetic data to {} (this may take a while)'.format(tempdir))
for i in range(5):
im, seg = create_test_image_3d(128, 128, 128, num_seg_classes=1)
n = nib.Nifti1Image(im, np.eye(4))
nib.save(n, os.path.join(tempdir, 'im%i.nii.gz' % i))
n = nib.Nifti1Image(seg, np.eye(4))
nib.save(n, os.path.join(tempdir, 'seg%i.nii.gz' % i))
images = sorted(glob(os.path.join(tempdir, 'im*.nii.gz')))
segs = sorted(glob(os.path.join(tempdir, 'seg*.nii.gz')))
# Define transforms for image and segmentation
imtrans = transforms.Compose([Rescale(), AddChannel()])
segtrans = transforms.Compose([AddChannel()])
ds = NiftiDataset(images,
segs,
transform=imtrans,
seg_transform=segtrans,
image_only=False)
device = torch.device("cuda:0")
net = UNet(
dimensions=3,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
def main():
monai.config.print_config()
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
# create a temporary directory and 40 random image, mask paris
tempdir = tempfile.mkdtemp()
print('generating synthetic data to {} (this may take a while)'.format(tempdir))
for i in range(40):
im, seg = create_test_image_3d(128, 128, 128, num_seg_classes=1)
n = nib.Nifti1Image(im, np.eye(4))
nib.save(n, os.path.join(tempdir, 'im%i.nii.gz' % i))
n = nib.Nifti1Image(seg, np.eye(4))
nib.save(n, os.path.join(tempdir, 'seg%i.nii.gz' % i))
images = sorted(glob(os.path.join(tempdir, 'im*.nii.gz')))
segs = sorted(glob(os.path.join(tempdir, 'seg*.nii.gz')))
# define transforms for image and segmentation
train_imtrans = Compose([
ScaleIntensity(),
AddChannel(),
RandSpatialCrop((96, 96, 96), random_size=False),
ToTensor()
])
train_segtrans = Compose([
AddChannel(),
RandSpatialCrop((96, 96, 96), random_size=False),
ToTensor()
])
val_imtrans = Compose([
ScaleIntensity(),
AddChannel(),
Resize((96, 96, 96)),
ToTensor()
])
val_segtrans = Compose([
AddChannel(),
Resize((96, 96, 96)),
ToTensor()
])
# define nifti dataset, data loader
check_ds = NiftiDataset(images, segs, transform=train_imtrans, seg_transform=train_segtrans)
check_loader = DataLoader(check_ds, batch_size=10, num_workers=2, pin_memory=torch.cuda.is_available())
im, seg = monai.utils.misc.first(check_loader)
print(im.shape, seg.shape)
# create a training data loader
train_ds = NiftiDataset(images[:20], segs[:20], transform=train_imtrans, seg_transform=train_segtrans)
train_loader = DataLoader(train_ds, batch_size=5, shuffle=True, num_workers=8, pin_memory=torch.cuda.is_available())
# create a validation data loader
val_ds = NiftiDataset(images[-20:], segs[-20:], transform=val_imtrans, seg_transform=val_segtrans)
val_loader = DataLoader(val_ds, batch_size=5, num_workers=8, pin_memory=torch.cuda.is_available())
# create UNet, DiceLoss and Adam optimizer
net = monai.networks.nets.UNet(
dimensions=3,
in_channels=1,
out_channels=1,
channels=(16, 32, 64, 128, 256),
strides=(2, 2, 2, 2),
num_res_units=2,
)
loss = monai.losses.DiceLoss(do_sigmoid=True)
lr = 1e-3
opt = torch.optim.Adam(net.parameters(), lr)
device = torch.device('cuda:0')
# ignite trainer expects batch=(img, seg) and returns output=loss at every iteration,
# user can add output_transform to return other values, like: y_pred, y, etc.
trainer = create_supervised_trainer(net, opt, loss, device, False)
# adding checkpoint handler to save models (network params and optimizer stats) during training
checkpoint_handler = ModelCheckpoint('./runs/', 'net', n_saved=10, require_empty=False)
trainer.add_event_handler(event_name=Events.EPOCH_COMPLETED,
handler=checkpoint_handler,
to_save={'net': net, 'opt': opt})
# StatsHandler prints loss at every iteration and print metrics at every epoch,
# we don't set metrics for trainer here, so just print loss, user can also customize print functions
# and can use output_transform to convert engine.state.output if it's not a loss value
train_stats_handler = StatsHandler(name='trainer')
train_stats_handler.attach(trainer)
# TensorBoardStatsHandler plots loss at every iteration and plots metrics at every epoch, same as StatsHandler
train_tensorboard_stats_handler = TensorBoardStatsHandler()
train_tensorboard_stats_handler.attach(trainer)
validation_every_n_epochs = 1
# Set parameters for validation
metric_name = 'Mean_Dice'
# add evaluation metric to the evaluator engine
val_metrics = {metric_name: MeanDice(add_sigmoid=True, to_onehot_y=False)}
# ignite evaluator expects batch=(img, seg) and returns output=(y_pred, y) at every iteration,
# user can add output_transform to return other values
evaluator = create_supervised_evaluator(net, val_metrics, device, True)
@trainer.on(Events.EPOCH_COMPLETED(every=validation_every_n_epochs))
def run_validation(engine):
evaluator.run(val_loader)
# add early stopping handler to evaluator
early_stopper = EarlyStopping(patience=4,
score_function=stopping_fn_from_metric(metric_name),
trainer=trainer)
evaluator.add_event_handler(event_name=Events.EPOCH_COMPLETED, handler=early_stopper)
# add stats event handler to print validation stats via evaluator
val_stats_handler = StatsHandler(
name='evaluator',
output_transform=lambda x: None, # no need to print loss value, so disable per iteration output
global_epoch_transform=lambda x: trainer.state.epoch) # fetch global epoch number from trainer
val_stats_handler.attach(evaluator)
# add handler to record metrics to TensorBoard at every validation epoch
val_tensorboard_stats_handler = TensorBoardStatsHandler(
output_transform=lambda x: None, # no need to plot loss value, so disable per iteration output
global_epoch_transform=lambda x: trainer.state.epoch) # fetch global epoch number from trainer
val_tensorboard_stats_handler.attach(evaluator)
# add handler to draw the first image and the corresponding label and model output in the last batch
# here we draw the 3D output as GIF format along Depth axis, at every validation epoch
val_tensorboard_image_handler = TensorBoardImageHandler(
batch_transform=lambda batch: (batch[0], batch[1]),
output_transform=lambda output: predict_segmentation(output[0]),
global_iter_transform=lambda x: trainer.state.epoch
)
evaluator.add_event_handler(event_name=Events.EPOCH_COMPLETED, handler=val_tensorboard_image_handler)
train_epochs = 30
state = trainer.run(train_loader, train_epochs)
shutil.rmtree(tempdir)
