transformers/docs/source/en/model_doc/dpt.md

DPT

Overview

The DPT model was proposed in Vision Transformers for Dense Prediction by René Ranftl, Alexey Bochkovskiy, Vladlen Koltun. DPT is a model that leverages the Vision Transformer (ViT) as backbone for dense prediction tasks like semantic segmentation and depth estimation.

The abstract from the paper is the following:

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into image-like representations at various resolutions and progressively combine them into full-resolution predictions using a convolutional decoder. The transformer backbone processes representations at a constant and relatively high resolution and has a global receptive field at every stage. These properties allow the dense vision transformer to provide finer-grained and more globally coherent predictions when compared to fully-convolutional networks. Our experiments show that this architecture yields substantial improvements on dense prediction tasks, especially when a large amount of training data is available. For monocular depth estimation, we observe an improvement of up to 28% in relative performance when compared to a state-of-the-art fully-convolutional network. When applied to semantic segmentation, dense vision transformers set a new state of the art on ADE20K with 49.02% mIoU. We further show that the architecture can be fine-tuned on smaller datasets such as NYUv2, KITTI, and Pascal Context where it also sets the new state of the art.

DPT architecture. Taken from the original paper.

This model was contributed by nielsr. The original code can be found here.

Usage tips

DPT is compatible with the [AutoBackbone] class. This allows to use the DPT framework with various computer vision backbones available in the library, such as [VitDetBackbone] or [Dinov2Backbone]. One can create it as follows:

from transformers import Dinov2Config, DPTConfig, DPTForDepthEstimation

# initialize with a Transformer-based backbone such as DINOv2
# in that case, we also specify `reshape_hidden_states=False` to get feature maps of shape (batch_size, num_channels, height, width)
backbone_config = Dinov2Config.from_pretrained("facebook/dinov2-base", out_features=["stage1", "stage2", "stage3", "stage4"], reshape_hidden_states=False)

config = DPTConfig(backbone_config=backbone_config)
model = DPTForDepthEstimation(config=config)

Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with DPT.

• Demo notebooks for [DPTForDepthEstimation] can be found here.

• Semantic segmentation task guide

• Monocular depth estimation task guide

If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

DPTConfig

autodoc DPTConfig

DPTFeatureExtractor

autodoc DPTFeatureExtractor - call - post_process_semantic_segmentation

DPTImageProcessor

autodoc DPTImageProcessor - preprocess - post_process_semantic_segmentation

DPTModel

autodoc DPTModel - forward

DPTForDepthEstimation

autodoc DPTForDepthEstimation - forward

DPTForSemanticSegmentation

autodoc DPTForSemanticSegmentation - forward