Move the network to device args: device - device to use. 'cpu' or 'cuda'

See :func:`BaseInstanceMasks.flip`.

Since teacher_model is registered as a plain object, it is necessary to put the teacher model to cuda when calling cuda function.

Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Build loss.

Convert a list of bboxes to roi format. Args: bbox_list (list[Tensor]): a list of bboxes corresponding to a batch of images.

See :func:`BaseInstanceMasks.expand`.

Apply function to a list of arguments. Note: This function applies the ``func`` to multiple inputs and map the multiple outputs o

Decode the predicted bboxes according to prediction and base boxes.

See :func:`BaseInstanceMasks.to_ndarray`.

Assign gt to bboxes. The assignment is done in following steps 1. compute iou between all bbox (bbox of all pyramid levels) and gt

Rebuild the network by calling the network function with the correct arguments.

Convert targets by image to targets by feature level. [target_img0, target_img1] -> [target_level0, target_level1, ...]

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Compute losses of the head. Args: cls_scores (list[Tensor]): Cls and quality scores for each scale level has shap

Unmap a subset of item (data) back to the original set of items (of size count)

Convert the model into training mode will keeping the normalization layer freezed.

Args: size (tuple): expected shape of dummy masks, (H, W) or (N, H, W) Return: ndarray: dummy mask

See :func:`BaseInstanceMasks.pad`.

Build detector.

Generate random bitmap masks for demo / testing purposes. Example: >>> from mmdet.core.mask.structures import BitmapMasks

Plot graph. Data is a 1D tensor. args: fig_num: Figure number. title: Title of figure.

Args: size (tuple): expected shape of dummy masks, (N, H, W) Return: list[list[ndarray]]: dummy mask

Initialize the weights of FPN module.

Set network to eval mode

Do training for the given number of epochs. args: max_epochs - Max number of training epochs, load_latest - Bool indic

Build head.

See :func:`BaseInstanceMasks.resize`.

Convert detection results to a list of numpy arrays. Args: bboxes (torch.Tensor | np.ndarray): shape (n, 5) labels (torch.Tensor

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1(ndarray): shape (n, 4) bboxes2(ndarray): shape (k, 4)

Builder of box sampler.

NMS for multi-class bboxes. Args: multi_bboxes (Tensor): shape (n, #class*4) or (n, 4) multi_scores (Tensor): shape (n, #class),

Decode distance prediction to bounding box. Args: points (Tensor): Shape (B, N, 2) or (N, 2). distance (Tensor): Distance from th

Transform network output for a batch into bbox predictions. Args: cls_scores (list[Tensor]): Box scores for each scale level

Generate grid anchors in multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Builder of box assigner.

Extract backbone features from the network. Expects a float tensor image with pixel range [0, 255].

Extract features. Args: img (torch.Tensor): Image tensor with shape (n, c, h ,w). Returns: list[torch.Tensor

Loss function of DIIHead, get loss of all images. Args: cls_score (Tensor): Classification prediction results of

Check if there exist a parameter with the given name.

Get targets for PAA head. This method is almost the same as `AnchorHead.get_targets()`. We direct return the results from _get_target

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions n

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class)

Get anchors according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_met

Calculate the ground truth for all samples in a batch according to the sampling_results. Almost the same as the implementation in bbo

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

Predicts IoU for the give proposals. args: modulation: Modulation vectors for the targets. Dims (batch, feature_dim).

Absolute value.

Encode deltas between bboxes and ground truth boxes.

nn.Module: the normalization layer named "norm1"

Obtain the mean of tensor on different GPUs.

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Get segmentation masks from mask_pred and bboxes. Args: mask_pred (Tensor or ndarray): shape (n, #class, h, w). F

dict: a dictionary of info about the object

Check if is ResNet building block.

Validate the output of the onnxruntime backend is the same as the output generated by torch. Args: model (nn.Module): the model to be