define dataset for ddp

Dataset to create indexes from `Sampler`. Args: sampler: PyTorch sampler

`MS Coco Detection <https://cocodataset.org/#detection-2016>`_ Dataset. It requires the `COCO API to be installed <https://github.com/pdollar/coc

Track a series of values and provide access to smoothed values over a window or the global series average.

Multi-head Attention block with relative position embeddings.

Multi-head Attention block with relative position embeddings.

Transformer blocks with support of window attention and residual propagation blocks

Transformer blocks with support of window attention and residual propagation blocks

Evaluate Panoptic Quality metrics on COCO using PanopticAPI. It saves panoptic segmentation prediction in `output_dir` It contains a syn

This wrapper is for loading the panoptic style annotation file. The format is shown in the CocoPanopticDataset class. Args: annotati

Evaluate Panoptic Quality metrics on COCO using PanopticAPI. It saves panoptic segmentation prediction in `output_dir` It contains a syn

Wrapper over `Sampler` for distributed training. Allows you to use any sampler in distributed mode. It is especially useful in conjunctio

A LayerNorm variant, popularized by Transformers, that performs point-wise mean and variance normalization over the channel dimension for inp

A LayerNorm variant, popularized by Transformers, that performs point-wise mean and variance normalization over the channel dimension for inp

Masked Autoencoder with VisionTransformer backbone

Image to Patch Embedding.

Image to Patch Embedding.

The standard bottleneck residual block without the last activation layer. It contains 3 conv layers with kernels 1x1, 3x3, 1x1.

The standard bottleneck residual block without the last activation layer. It contains 3 conv layers with kernels 1x1, 3x3, 1x1.

Coco dataset for Panoptic segmentation. The annotation format is shown as follows. The `ann` field is optional for testing. .. code-bloc

Randomly change the brightness, contrast, saturation and hue of an image. If the image is torch Tensor, it is expected to have [..., 1 or 3, H

Composes several transforms together. This transform does not support torchscript. Please, see the note below. Args: transforms (list

Gaussian blur augmentation from SimCLR: https://arxiv.org/abs/2002.05709

LARS optimizer, no rate scaling or weight decay for parameters <= 1D.

Normalize a tensor image with mean and standard deviation. This transform does not support PIL Image. Given mean: ``(mean[1],...,mean[n])`` an

Apply randomly a list of transformations with a given probability. .. note:: In order to script the transformation, please use ``torch.nn.

Randomly selects a rectangle region in a torch.Tensor image and erases its pixels. This transform does not support PIL Image. 'Random Erasing

Horizontally flip the given image randomly with a given probability. If the image is torch Tensor, it is expected to have [..., H, W] shape, w

Crop a random portion of image and resize it to a given size. If the image is torch Tensor, it is expected to have [..., H, W] shape, where ..

RandomResizedCrop for matching TF/TPU implementation: no for-loop is used. This may lead to results different with torchvision's version.

Save PanoInst Masks

Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. This transform does not support torchscript. Converts a PIL Image or numpy.ndarray (H x W

CocoDataset dataset for top-down pose estimation. "Microsoft COCO: Common Objects in Context", ECCV'2014. More details can be found in the `p

CocoDataset dataset for top-down pose estimation. "Microsoft COCO: Common Objects in Context", ECCV'2014. More details can be found in the `p

Top-down pose detectors. Args: backbone (dict): Backbone modules to extract feature. keypoint_head (dict): Keypoint head to proce

Top-down pose detectors. Args: backbone (dict): Backbone modules to extract feature. keypoint_head (dict): Keypoint head to proce

Generate the target heatmap. Required key: 'joints_3d', 'joints_3d_visible', 'ann_info'. Modified key: 'target', and 'target_weight'. A

Generate the target heatmap. Required key: 'joints_3d', 'joints_3d_visible', 'ann_info'. Modified key: 'target', and 'target_weight'. A