Swaps the complex dimension with the channel dimension so that the network treats real/imaginary parts as two separate channels. Args:

ResNet-18 with optional pretrained support when `spatial_dims` is 3. Pretraining from `Med3D: Transfer Learning for 3D Medical Image Analysis <ht

ResNet-50 with optional pretrained support when `spatial_dims` is 3. Pretraining from `Med3D: Transfer Learning for 3D Medical Image Analysis <ht

Recursively resolve `self.config` to replace the relative ids with absolute ids, for example, `@##A` means `A` in the upper level. an

Returns a RetinaNet detector using a ResNet-50 as backbone, which can be pretrained from `Med3D: Transfer Learning for 3D Medical Image Analy

Similar to np.roll but applies to PyTorch Tensors Args: x: input data (k-space or image) that can be 1) real-valued: the

Launch the Algos. This is useful for light-weight Algos where there's no need to distribute the training jobs. If the generated Algo

Securely verify compressed package member paths to prevent path traversal attacks

Sampling function for the VQVAE + Transformer model. Args: latent_spatial_dim: shape of the sampled image. s

Sample points from labels. Args: labels: [1, 1, H, W, D] label_set: local index, must match values in labels. max_ppoint:

From the mean and sigma representations resulting of encoding an image through the latent space, obtains a noise sample resulting fro

Save a batch of data into the cache dictionary. Args: batch_data: target batch data content that save into cache. met

Postprocessing to generate detection result from classification logits and boxes. The box selection is performed with the following

For element in labels, select indices keep from it. Args: labels: Sequence of array. Each element represents classification labels o

Expands an image to its corresponding coil images based on the given sens_maps. Let's say there are C coils. This function multiples image im

Reduces coil measurements to a corresponding image based on the given sens_maps. Let's say there are C coil measurements inside kspace, then

Using for training. Set ATSS matcher that matches anchors with ground truth boxes Args: num_candidates: number of positi

Set the input data and run deterministic transforms to generate cache content. Note: should call this func after an entire epoch and

Set the bundle ensemble method name and parameters for save image transform parameters. Args: ensemble_method_name: the

Using for training. Set hard negative sampler that samples part of the anchors for training. HardNegativeSampler is used to suppress

Set parameters for the HPO module and the algos before the training. It will attempt to (1) override bundle templates with the key-va

look up `name` in `mod` and replace the layer with `new_layer`, return the updated `mod`. Args: mod: a pytorch module to be updated.

Set the number of cross validation folds for all algos. Args: num_fold: a positive integer to define the number of folds

Set seed or random state for all randomizable properties of obj. Args: obj: object to set seed or random state for. seed: se

Sets swish function as memory efficient (for training) or standard (for export). Args: memory_efficient (bool): Whether to use me

Set trainer to execute early stop if not setting properly in `__init__()`.

Perform soft erosion on the input image Args: img: the shape should be BCH(WD) Adapted from: https://github.com/jocpae/

Wrapper function to perform soft opening on the input image Args: img: the shape should be BCH(WD) Adapted from: https:

Perform soft skeletonization on the input image Adapted from: https://github.com/jocpae/clDice/blob/master/cldice_loss/pytorch/soft_s

stable softplus through `np.logaddexp` with equivalent implementation for torch. Args: x: array/tensor. Returns: Softplus of

Return a new sorted dictionary from the `item`.

This function generate the new boxes when the corresponding image is cropped to the given ROI. When ``remove_empty=True``, it makes sure the

compute squarepulse using pytorch equivalent to numpy implementation from https://docs.scipy.org/doc/scipy/reference/generated/scipy.sign

When boxes are empty, this function standardize it to shape of (0,4) or (0,6). Args: boxes: bounding boxes, Nx4 or Nx6 or empty torc

Returns a status string for the current state of the engine.

Predict the sample at the previous timestep by reversing the SDE. Core function to propagate the diffusion process from the learned m

Predicts the next sample in the diffusion process. Args: model_output (torch.Tensor): Output from the trained diffusion

Utility function for distributed data parallel to all gather a list of strings. Refer to the idea of ignite `all_gather(string)`: https:/

Interchange two axes of boxes. Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be ``Stan

Applies a transformation to the timestep based on image resolution scaling. Args: t (torch.Tensor): The original timestep(s).

Return a block string notation for current BlockArgs object Returns: A string notation of BlockArgs object arguments.

Given a dictionary whose values contain scalars or tuples (with the same length as ``keys``), Create a dictionary for each key containing the

Train on client's local data. Args: data: `ExchangeObject` containing the current global model weights. extr

Build the shell command string for training a single nnU-Net model. Args: config: Configuration name (e.g., "3d_fullres"

The keys to store necessary info of an applied transform.

Update the metadata from the output of `MetaTensor.__torch_function__`. The output of `torch.Tensor.__torch_function__` could be a s

Exact VISTA3D network configuration used in https://arxiv.org/abs/2406.05285>`_. The model treats class index larger than 132 as zero-shot.

window partition operation based on: "Liu et al., Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/a

Utility function to write the metrics into files, contains 3 parts: 1. if `metrics` dict is not None, write overall metrics into file, every

This method should take raw model outputs as inputs, and return values that measure the models' quality.

Apply the transform to `img`.

Defines a network accept input with `in_channels` channels, output of `out_channels` channels, and hidden layers with channels given

Args: spatial_dims: number of spatial dimensions of the input image. in_channels: number of channels of the input ima

Args: patch_size: dimension of patch size. in_chans: dimension of input channels. embed_dim: number of li

For pytorch native APIs, the possible values are: - mode: ``"nearest"``, ``"bilinear"``, ``"bicubic"``. - padding_mo