Parse information from a line in a requirements text file.

Monkey-patch an existing `DataParallel` object. Add the replication callback. Useful when you have customized `DataParallel` implementation.

Convert pre-eval results to metrics. Args: pre_eval_results (list[tuple[torch.Tensor]]): per image eval results for computing

Convert pre-eval results to metrics. Args: pre_eval_results (list[tuple[torch.Tensor]]): per image eval results for computing

Prepares the arguments needed for get_metrics. When training on TPUs, this function should be executed on TPU. Args: generator_inputs:

Get testing data after pipeline. Args: idx (int): Index of data. Returns: dict: Testing data after pipeline

Get testing data after pipeline. Args: idx (int): Index of data. Returns: dict: Testing data after pipeline

Get training data and annotations after pipeline. Args: idx (int): Index of data. Returns: dict: Training da

Get training data and annotations after pipeline. Args: idx (int): Index of data. Returns: dict: Training da

Provides dataset of ImageNet digits that were preprocessed by the Red Team. Args: batch_size: The number of images in each batch. shu

Forward function of PSP module.

Forward function of PSP module.

Export Pytorch model to TorchScript model and verify the outputs are same between Pytorch and TorchScript. Args: model (nn.Module): P

Export Pytorch model to TorchScript model and verify the outputs are same between Pytorch and TorchScript. Args: model (nn.Module): P

Export Pytorch model to ONNX model and verify the outputs are same between Pytorch and ONNX. Args: model (nn.Module): Pytorch model w

Export Pytorch model to ONNX model and verify the outputs are same between Pytorch and ONNX. Args: model (nn.Module): Pytorch model w

Randomly select an img_scale from given candidates. Args: img_scales (list[tuple]): Images scales for selection. Returns

Randomly select an img_scale from given candidates. Args: img_scales (list[tuple]): Images scales for selection. Returns

Randomly select an img_scale from given candidates. Args: img_scales (list[tuple]): Images scales for selection. Returns

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are "none", "mean" and "sum".

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are "none", "mean" and "sum".

Reduce mean when distributed training.

Reduce mean when distributed training.

Register an slave device. Args: identifier: an identifier, usually is the device id. Returns: a `SlavePipe` obj

Write the segmentation results to images. Args: results (list[ndarray]): Testing results of the dataset.

Write the segmentation results to images. Args: results (list[ndarray]): Testing results of the dataset.

Write the segmentation results to images. Args: results (list[ndarray]): Testing results of the dataset.

Write the segmentation results to images. Args: results (list[ndarray]): Testing results of the dataset.

Write the segmentation results to images. Args: results (list[ndarray]): Testing results of the dataset.

Write the segmentation results to images. Args: results (list[ndarray]): Testing results of the dataset.

Main entry for the master device in each forward pass. The messages were first collected from each devices (including the master devi

Sample pixels that have high loss or with low prediction confidence. Args: seg_logit (torch.Tensor): segmentation logits, shape (

Sample pixels that have high loss or with low prediction confidence. Args: seg_logit (torch.Tensor): segmentation logits, shape (

Saturation distortion.

Saturation distortion.

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

Placeholder for single image test.

Placeholder for single image test.

Inference by sliding-window with overlap. If h_crop > h_img or w_crop > w_img, the small patch will be used to decode without padding

Inference by sliding-window with overlap. If h_crop > h_img or w_crop > w_img, the small patch will be used to decode without padding

Calculate Total Intersection and Union. Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or li

Calculate Total Intersection and Union. Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or li

Launch segmentor training.

Inference with full image.

Inference with full image.

Args: windows: (num_windows*B, window_size, window_size, C) H (int): Height of image W (int): Width of im

Args: windows: (num_windows*B, window_size, window_size, C) H (int): Height of image W (int): Width of im

Call function to resize images, bounding boxes, masks, semantic segmentation map. Args: results (dict): Result dict from

Call function to load images into results. Args: results (dict): A result dict contains the file name of the imag

Call function to apply test time augment transforms on results. Args: results (dict): Result dict contains the data to transform.

Call function to resize images, semantic segmentation map to multiple of size divisor. Args: results (dict): Result dict

Call function to resize images, bounding boxes, masks, semantic segmentation map. Args: results (dict): Result dict from

Call function to flip bounding boxes, masks, semantic segmentation maps. Args: results (dict): Result dict from loading p

Call function to pad images, masks, semantic segmentation maps. Args: results (dict): Result dict from loading pipeline.

Call function to normalize images. Args: results (dict): Result dict from loading pipeline. Returns: dict: N

Call function to rerange images. Args: results (dict): Result dict from loading pipeline. Returns: dict: Rera

Call function to Use CLAHE method process images. Args: results (dict): Result dict from loading pipeline. Returns:

Call function to randomly crop images, semantic segmentation maps. Args: results (dict): Result dict from loading pipeline.

Call function to rotate image, semantic segmentation maps. Args: results (dict): Result dict from loading pipeline. Retu

Call function to convert RGB image to grayscale image. Args: results (dict): Result dict from loading pipeline. Returns:

Call function to process the image with gamma correction. Args: results (dict): Result dict from loading pipeline. Retur

Call function to scale the semantic segmentation map. Args: results (dict): Result dict from loading pipeline. Returns:

Call function to perform photometric distortion on images. Args: results (dict): Result dict from loading pipeline. Retu

Call function to drop some regions of image.

Call function to make a mosaic of image. Args: results (dict): Result dict. Returns: dict: Result dict with

Call functions to load image and get image meta information. Args: results (dict): Result dict from :obj:`mmseg.CustomDataset`.

Call function to load multiple types annotations. Args: results (dict): Result dict from :obj:`mmseg.CustomDataset`. Ret

Call function to apply transforms sequentially. Args: data (dict): A result dict contains the data to transform. Returns