A conv block that bundles conv/norm/activation layers. This block simplifies the usage of convolution layers, which are commonly used with a

r""" https://huggingface.co/spaces/Roll20/pet_score/blob/b258ef28152ab0d5b377d9142a23346f863c1526/lib/timm/models/convnext.py#L85 LayerNorm for c

Pads images such that dimensions are divisible by 8

Apply Gaussian Blur to the PIL image.

Collection of assign results.

Encoder Decoder depther. EncoderDecoder typically consists of backbone and decode_head.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor, or keep as is if already a tensor.

ResidualConvUnit, pre-activate residual unit. Args: in_channels (int): number of channels in the input feature map. act_cfg (dict)

ResidualConvUnit, pre-activate residual unit. Args: in_channels (int): number of channels in the input feature map. act_layer (nn.

Residual convolution module.

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

Applies padding to input (if needed) so that input can get fully covered by filter you specified. It support two modes "same" and "corner". The

Just a batchnorm.

Vision Transformers for Dense Prediction. This head is implemented of `DPT <https://arxiv.org/abs/2103.13413>`_. Args: embed_dims (int

Feature fusion block.

FeatureFusionBlock, merge feature map from different stages. Args: in_channels (int): Input channels. act_cfg (dict): The activati

FeatureFusionBlock, merge feature map from different stages. Args: in_channels (int): Input channels. act_layer (nn.Module): activ

Kozachenko-Leonenko entropic loss regularizer from Sablayrolles et al. - 2018 - Spreading vectors for similarity search

Linear layer to train on top of frozen features

Mask sampling result.

Standard points generator for multi-level (Mlvl) feature maps in 2D points-based detectors. Args: strides (list[int] | list[tuple[int

ViTPostProcessBlock, process cls_token in ViT backbone output and rearrange the feature vector to feature map. Args: in_channels (int)

ViTPostProcessBlock, process cls_token in ViT backbone output and rearrange the feature vector to feature map. Args: in_channels (int)

Bbox sampling result. Example: >>> # xdoctest: +IGNORE_WANT >>> from mmdet.core.bbox.samplers.sampling_result import * # NOQA