update 2d_segmentation (#803)

Author: KumoLiu

2d_segmentation/torch/unet_evaluation_array.py

@@ -17,14 +17,13 @@
 
 import torch
 from PIL import Image
-from torch.utils.data import DataLoader
 
 from monai import config
-from monai.data import ArrayDataset, create_test_image_2d, decollate_batch
+from monai.data import ArrayDataset, create_test_image_2d, decollate_batch, DataLoader
 from monai.inferers import sliding_window_inference
 from monai.metrics import DiceMetric
 from monai.networks.nets import UNet
-from monai.transforms import Activations, AddChannel, AsDiscrete, Compose, LoadImage, SaveImage, ScaleIntensity, EnsureType
+from monai.transforms import Activations, AddChannel, AsDiscrete, Compose, LoadImage, SaveImage, ScaleIntensity
 
 
 def main(tempdir):
@@ -41,13 +40,13 @@ def main(tempdir):
     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()])
+    imtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
+    segtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
     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)])
+    post_trans = Compose([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(

2d_segmentation/torch/unet_evaluation_dict.py

@@ -17,14 +17,13 @@
 
 import torch
 from PIL import Image
-from torch.utils.data import DataLoader
 
 import monai
-from monai.data import create_test_image_2d, list_data_collate, decollate_batch
+from monai.data import create_test_image_2d, list_data_collate, decollate_batch, DataLoader
 from monai.inferers import sliding_window_inference
 from monai.metrics import DiceMetric
 from monai.networks.nets import UNet
-from monai.transforms import Activations, AddChanneld, AsDiscrete, Compose, LoadImaged, SaveImage, ScaleIntensityd, EnsureTyped, EnsureType
+from monai.transforms import Activations, AddChanneld, AsDiscrete, Compose, LoadImaged, SaveImage, ScaleIntensityd
 
 
 def main(tempdir):
@@ -47,14 +46,13 @@ def main(tempdir):
             LoadImaged(keys=["img", "seg"]),
             AddChanneld(keys=["img", "seg"]),
             ScaleIntensityd(keys=["img", "seg"]),
-            EnsureTyped(keys=["img", "seg"]),
         ]
     )
     val_ds = monai.data.Dataset(data=val_files, transform=val_transforms)
     # sliding window inference need to input 1 image in every iteration
     val_loader = DataLoader(val_ds, batch_size=1, num_workers=4, collate_fn=list_data_collate)
     dice_metric = DiceMetric(include_background=True, reduction="mean", get_not_nans=False)
-    post_trans = Compose([EnsureType(), Activations(sigmoid=True), AsDiscrete(threshold=0.5)])
+    post_trans = Compose([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(

2d_segmentation/torch/unet_training_array.py

@@ -17,11 +17,10 @@
 
 import torch
 from PIL import Image
-from torch.utils.data import DataLoader
 from torch.utils.tensorboard import SummaryWriter
 
 import monai
-from monai.data import ArrayDataset, create_test_image_2d, decollate_batch
+from monai.data import ArrayDataset, create_test_image_2d, decollate_batch, DataLoader
 from monai.inferers import sliding_window_inference
 from monai.metrics import DiceMetric
 from monai.transforms import (
@@ -33,7 +32,6 @@
     RandRotate90,
     RandSpatialCrop,
     ScaleIntensity,
-    EnsureType,
 )
 from monai.visualize import plot_2d_or_3d_image
 
@@ -60,7 +58,6 @@ def main(tempdir):
             ScaleIntensity(),
             RandSpatialCrop((96, 96), random_size=False),
             RandRotate90(prob=0.5, spatial_axes=(0, 1)),
-            EnsureType(),
         ]
     )
     train_segtrans = Compose(
@@ -70,11 +67,10 @@ def main(tempdir):
             ScaleIntensity(),
             RandSpatialCrop((96, 96), random_size=False),
             RandRotate90(prob=0.5, spatial_axes=(0, 1)),
-            EnsureType(),
         ]
     )
-    val_imtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity(), EnsureType()])
-    val_segtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity(), EnsureType()])
+    val_imtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
+    val_segtrans = Compose([LoadImage(image_only=True), AddChannel(), ScaleIntensity()])
 
     # define array dataset, data loader
     check_ds = ArrayDataset(images, train_imtrans, segs, train_segtrans)
@@ -89,7 +85,7 @@ def main(tempdir):
     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", get_not_nans=False)
-    post_trans = Compose([EnsureType(), Activations(sigmoid=True), AsDiscrete(threshold=0.5)])
+    post_trans = Compose([Activations(sigmoid=True), AsDiscrete(threshold=0.5)])
     # create UNet, DiceLoss and Adam optimizer
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     model = monai.networks.nets.UNet(

2d_segmentation/torch/unet_training_dict.py

@@ -17,11 +17,10 @@
 
 import torch
 from PIL import Image
-from torch.utils.data import DataLoader
 from torch.utils.tensorboard import SummaryWriter
 
 import monai
-from monai.data import create_test_image_2d, list_data_collate, decollate_batch
+from monai.data import create_test_image_2d, list_data_collate, decollate_batch, DataLoader
 from monai.inferers import sliding_window_inference
 from monai.metrics import DiceMetric
 from monai.transforms import (
@@ -33,8 +32,6 @@
     RandCropByPosNegLabeld,
     RandRotate90d,
     ScaleIntensityd,
-    EnsureTyped,
-    EnsureType,
 )
 from monai.visualize import plot_2d_or_3d_image
 
@@ -65,15 +62,13 @@ def main(tempdir):
                 keys=["img", "seg"], label_key="seg", spatial_size=[96, 96], pos=1, neg=1, num_samples=4
             ),
             RandRotate90d(keys=["img", "seg"], prob=0.5, spatial_axes=[0, 1]),
-            EnsureTyped(keys=["img", "seg"]),
         ]
     )
     val_transforms = Compose(
         [
             LoadImaged(keys=["img", "seg"]),
             AddChanneld(keys=["img", "seg"]),
             ScaleIntensityd(keys=["img", "seg"]),
-            EnsureTyped(keys=["img", "seg"]),
         ]
     )
 
@@ -99,7 +94,7 @@ def main(tempdir):
     val_ds = monai.data.Dataset(data=val_files, transform=val_transforms)
     val_loader = DataLoader(val_ds, batch_size=1, num_workers=4, collate_fn=list_data_collate)
     dice_metric = DiceMetric(include_background=True, reduction="mean", get_not_nans=False)
-    post_trans = Compose([EnsureType(), Activations(sigmoid=True), AsDiscrete(threshold=0.5)])
+    post_trans = Compose([Activations(sigmoid=True), AsDiscrete(threshold=0.5)])
     # create UNet, DiceLoss and Adam optimizer
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     model = monai.networks.nets.UNet(