Transformers documentation

Depth Anything V2

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Depth Anything V2

Overview

Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything model, but uses synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions.

The abstract from the paper is the following:

This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation model. Notably, compared with V1, this version produces much finer and more robust depth predictions through three key practices: 1) replacing all labeled real images with synthetic images, 2) scaling up the capacity of our teacher model, and 3) teaching student models via the bridge of large-scale pseudo-labeled real images. Compared with the latest models built on Stable Diffusion, our models are significantly more efficient (more than 10x faster) and more accurate. We offer models of different scales (ranging from 25M to 1.3B params) to support extensive scenarios. Benefiting from their strong generalization capability, we fine-tune them with metric depth labels to obtain our metric depth models. In addition to our models, considering the limited diversity and frequent noise in current test sets, we construct a versatile evaluation benchmark with precise annotations and diverse scenes to facilitate future research.

drawing Depth Anything overview. Taken from the original paper.

The Depth Anything models were contributed by nielsr. The original code can be found here.

Usage example

There are 2 main ways to use Depth Anything V2: either using the pipeline API, which abstracts away all the complexity for you, or by using the DepthAnythingForDepthEstimation class yourself.

Pipeline API

The pipeline allows to use the model in a few lines of code:

>>> from transformers import pipeline
>>> from PIL import Image
>>> import requests

>>> # load pipe
>>> pipe = pipeline(task="depth-estimation", model="depth-anything/Depth-Anything-V2-Small-hf")

>>> # load image
>>> url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> # inference
>>> depth = pipe(image)["depth"]

Using the model yourself

If you want to do the pre- and post-processing yourself, here’s how to do that:

>>> from transformers import AutoImageProcessor, AutoModelForDepthEstimation
>>> import torch
>>> import numpy as np
>>> from PIL import Image
>>> import requests

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> image_processor = AutoImageProcessor.from_pretrained("depth-anything/Depth-Anything-V2-Small-hf")
>>> model = AutoModelForDepthEstimation.from_pretrained("depth-anything/Depth-Anything-V2-Small-hf")

>>> # prepare image for the model
>>> inputs = image_processor(images=image, return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model(**inputs)
...     predicted_depth = outputs.predicted_depth

>>> # interpolate to original size
>>> prediction = torch.nn.functional.interpolate(
...     predicted_depth.unsqueeze(1),
...     size=image.size[::-1],
...     mode="bicubic",
...     align_corners=False,
... )

>>> # visualize the prediction
>>> output = prediction.squeeze().cpu().numpy()
>>> formatted = (output * 255 / np.max(output)).astype("uint8")
>>> depth = Image.fromarray(formatted)

Resources

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

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.

DepthAnythingConfig

class transformers.DepthAnythingConfig

< >

( backbone_config = None backbone = None use_pretrained_backbone = False use_timm_backbone = False backbone_kwargs = None patch_size = 14 initializer_range = 0.02 reassemble_hidden_size = 384 reassemble_factors = [4, 2, 1, 0.5] neck_hidden_sizes = [48, 96, 192, 384] fusion_hidden_size = 64 head_in_index = -1 head_hidden_size = 32 depth_estimation_type = 'relative' max_depth = None **kwargs )

Parameters

  • backbone_config (Union[Dict[str, Any], PretrainedConfig], optional) — The configuration of the backbone model. Only used in case is_hybrid is True or in case you want to leverage the AutoBackbone API.
  • backbone (str, optional) — Name of backbone to use when backbone_config is None. If use_pretrained_backbone is True, this will load the corresponding pretrained weights from the timm or transformers library. If use_pretrained_backbone is False, this loads the backbone’s config and uses that to initialize the backbone with random weights.
  • use_pretrained_backbone (bool, optional, defaults to False) — Whether to use pretrained weights for the backbone.
  • use_timm_backbone (bool, optional, defaults to False) — Whether or not to use the timm library for the backbone. If set to False, will use the AutoBackbone API.
  • backbone_kwargs (dict, optional) — Keyword arguments to be passed to AutoBackbone when loading from a checkpoint e.g. {'out_indices': (0, 1, 2, 3)}. Cannot be specified if backbone_config is set.
  • patch_size (int, optional, defaults to 14) — The size of the patches to extract from the backbone features.
  • initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • reassemble_hidden_size (int, optional, defaults to 384) — The number of input channels of the reassemble layers.
  • reassemble_factors (List[int], optional, defaults to [4, 2, 1, 0.5]) — The up/downsampling factors of the reassemble layers.
  • neck_hidden_sizes (List[str], optional, defaults to [48, 96, 192, 384]) — The hidden sizes to project to for the feature maps of the backbone.
  • fusion_hidden_size (int, optional, defaults to 64) — The number of channels before fusion.
  • head_in_index (int, optional, defaults to -1) — The index of the features to use in the depth estimation head.
  • head_hidden_size (int, optional, defaults to 32) — The number of output channels in the second convolution of the depth estimation head.
  • depth_estimation_type (str, optional, defaults to "relative") — The type of depth estimation to use. Can be one of ["relative", "metric"].
  • max_depth (float, optional) — The maximum depth to use for the “metric” depth estimation head. 20 should be used for indoor models and 80 for outdoor models. For “relative” depth estimation, this value is ignored.

This is the configuration class to store the configuration of a DepthAnythingModel. It is used to instantiate a DepthAnything model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DepthAnything LiheYoung/depth-anything-small-hf architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Example:

>>> from transformers import DepthAnythingConfig, DepthAnythingForDepthEstimation

>>> # Initializing a DepthAnything small style configuration
>>> configuration = DepthAnythingConfig()

>>> # Initializing a model from the DepthAnything small style configuration
>>> model = DepthAnythingForDepthEstimation(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

to_dict

< >

( )

Serializes this instance to a Python dictionary. Override the default to_dict(). Returns: Dict[str, any]: Dictionary of all the attributes that make up this configuration instance,

DepthAnythingForDepthEstimation

class transformers.DepthAnythingForDepthEstimation

< >

( config )

Parameters

  • config (DepthAnythingConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Depth Anything Model with a depth estimation head on top (consisting of 3 convolutional layers) e.g. for KITTI, NYUv2.

This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( pixel_values: FloatTensor labels: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) transformers.modeling_outputs.DepthEstimatorOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See DPTImageProcessor.call() for details.
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
  • labels (torch.LongTensor of shape (batch_size, height, width), optional) — Ground truth depth estimation maps for computing the loss.

Returns

transformers.modeling_outputs.DepthEstimatorOutput or tuple(torch.FloatTensor)

A transformers.modeling_outputs.DepthEstimatorOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (DepthAnythingConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.

  • predicted_depth (torch.FloatTensor of shape (batch_size, height, width)) — Predicted depth for each pixel.

  • hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, num_channels, height, width).

    Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

  • attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, patch_size, sequence_length).

    Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The DepthAnythingForDepthEstimation forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

>>> from transformers import AutoImageProcessor, AutoModelForDepthEstimation
>>> import torch
>>> import numpy as np
>>> from PIL import Image
>>> import requests

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> image_processor = AutoImageProcessor.from_pretrained("LiheYoung/depth-anything-small-hf")
>>> model = AutoModelForDepthEstimation.from_pretrained("LiheYoung/depth-anything-small-hf")

>>> # prepare image for the model
>>> inputs = image_processor(images=image, return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model(**inputs)
...     predicted_depth = outputs.predicted_depth

>>> # interpolate to original size
>>> prediction = torch.nn.functional.interpolate(
...     predicted_depth.unsqueeze(1),
...     size=image.size[::-1],
...     mode="bicubic",
...     align_corners=False,
... )

>>> # visualize the prediction
>>> output = prediction.squeeze().cpu().numpy()
>>> formatted = (output * 255 / np.max(output)).astype("uint8")
>>> depth = Image.fromarray(formatted)
< > Update on GitHub