Update 3d-segmentation tutorials (#916)

* easy-integrate-bundle-v1

Signed-off-by: KumoLiu <yunl@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add multigpu  implementation

Signed-off-by: KumoLiu <yunl@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* minor fix

Signed-off-by: KumoLiu <yunl@nvidia.com>

* del remove file

Signed-off-by: KumoLiu <yunl@nvidia.com>

Signed-off-by: KumoLiu <yunl@nvidia.com>

Author: KumoLiu

3d_segmentation/challenge_baseline/README.md

@@ -64,7 +64,7 @@ During training, the top three models will be selected based on the per-epoch va
 
 The training uses convenient file loading modules and a few intensity and spatial random augmentations using [MONAI](https://github.com/Project-MONAI/MONAI):
 
-- `LoadImaged`, `AddChanneld`, `Orientationd`, `Spacingd`, `ScaleIntensityRanged`
+- `LoadImaged`, `Orientationd`, `Spacingd`, `ScaleIntensityRanged`
 
 Load the image data into the LPS orientation (Left to right, Posterior to anterior, Superior to inferior), with a resolution of 1.25mm x 1.25mm x 5.00mm, and intensity between [-1000.0, 500.0] scaled to [0.0, 1.0].
 

3d_segmentation/swin_unetr_brats21_segmentation_3d.ipynb

@@ -479,7 +479,7 @@
     "torch.backends.cudnn.benchmark = True\n",
     "dice_loss = DiceLoss(to_onehot_y=False, sigmoid=True)\n",
     "post_sigmoid = Activations(sigmoid=True)\n",
-    "post_pred = AsDiscrete(argmax=False, logit_thresh=0.5)\n",
+    "post_pred = AsDiscrete(argmax=False, threshold=0.5)\n",
     "dice_acc = DiceMetric(\n",
     "    include_background=True, reduction=MetricReduction.MEAN_BATCH, get_not_nans=True\n",
     ")\n",