Mosaic transform function for label annotations. Args: results (dict): Result dict. Returns: dict: Updated r

Mosaic transform function for label annotations. Args: results (dict): Result dict. Returns: dict: Updated r

Pad images according to ``self.size``.

Pad images according to ``self.size``.

Pad masks according to ``results['pad_shape']``.

Pad masks according to ``results['pad_shape']``.

Positiong embeding method. Resize the pos_embed, if the input image size doesn't match the training size. Args:

Positiong embeding method. Resize the pos_embed, if the input image size doesn't match the training size. Args:

Returns function for processing the elements of the imagenet dataset.

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Resize images with ``results['scale']``.

Resize images with ``results['scale']``.

Resize images with ``results['scale']``.

Resize semantic segmentation map with ``results['scale']``.

Resize semantic segmentation map with ``results['scale']``.

Resize semantic segmentation map with ``results['scale']``.

Add extra files that are required to support MIM into the package. These files will be added by creating a symlink to the originals if the pa

Placeholder for augmentation test.

Placeholder for augmentation test.

Brightness distortion.

Brightness distortion.

Build pixel sampler for segmentation map.

Build pixel sampler for segmentation map.

CAM feature classification.

CAM feature classification.

Maps value x from range [a, b] to range [c, d]

Gathers variables from different GPUs on a specified device (-1 means the CPU), with dictionary support.

Placeholder for extract features from images.

Placeholder for extract features from images.

calculate the f-score value. Args: precision (float | torch.Tensor): The precision value. recall (float | torch.Tensor): The reca

calculate the f-score value. Args: precision (float | torch.Tensor): The precision value. recall (float | torch.Tensor): The reca

This function is for finding the latest checkpoint. It will be used when automatically resume, modified from https://github.com/open-mmlab/mm

This function is for finding the latest checkpoint. It will be used when automatically resume, modified from https://github.com/open-mmlab/mm

Forward function.

Forward function.

Forward function.

Forward function.

Forward function.

Forward function.

return x GiB.

return x GiB.

Get Inception activations. Use TF-GAN utility to avoid holding images or Inception activations in memory all at once. Args: get_im

Get Inception activations. Args: image_ds: tf.Dataset for images. num_batches: The number of batches to fetch at a time. get_lo

Get class names of current dataset. Args: classes (Sequence[str] | str | None): If classes is None, use default C