Transformers documentation

SegFormer

Join the Hugging Face community

and get access to the augmented documentation experience

to get started

# SegFormer

## Overview

The SegFormer model was proposed in SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo. The model consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on image segmentation benchmarks such as ADE20K and Cityscapes.

The abstract from the paper is the following:

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a novel hierarchically structured Transformer encoder which outputs multiscale features. It does not need positional encoding, thereby avoiding the interpolation of positional codes which leads to decreased performance when the testing resolution differs from training. 2) SegFormer avoids complex decoders. The proposed MLP decoder aggregates information from different layers, and thus combining both local attention and global attention to render powerful representations. We show that this simple and lightweight design is the key to efficient segmentation on Transformers. We scale our approach up to obtain a series of models from SegFormer-B0 to SegFormer-B5, reaching significantly better performance and efficiency than previous counterparts. For example, SegFormer-B4 achieves 50.3% mIoU on ADE20K with 64M parameters, being 5x smaller and 2.2% better than the previous best method. Our best model, SegFormer-B5, achieves 84.0% mIoU on Cityscapes validation set and shows excellent zero-shot robustness on Cityscapes-C.

The figure below illustrates the architecture of SegFormer. Taken from the original paper.

This model was contributed by nielsr. The TensorFlow version of the model was contributed by sayakpaul. The original code can be found here.

Tips:

• SegFormer consists of a hierarchical Transformer encoder, and a lightweight all-MLP decoder head. SegformerModel is the hierarchical Transformer encoder (which in the paper is also referred to as Mix Transformer or MiT). SegformerForSemanticSegmentation adds the all-MLP decoder head on top to perform semantic segmentation of images. In addition, there’s SegformerForImageClassification which can be used to - you guessed it - classify images. The authors of SegFormer first pre-trained the Transformer encoder on ImageNet-1k to classify images. Next, they throw away the classification head, and replace it by the all-MLP decode head. Next, they fine-tune the model altogether on ADE20K, Cityscapes and COCO-stuff, which are important benchmarks for semantic segmentation. All checkpoints can be found on the hub.
• The quickest way to get started with SegFormer is by checking the example notebooks (which showcase both inference and fine-tuning on custom data). One can also check out the blog post introducing SegFormer and illustrating how it can be fine-tuned on custom data.
• TensorFlow users should refer to this repository that shows off-the-shelf inference and fine-tuning.
• One can also check out this interactive demo on Hugging Face Spaces to try out a SegFormer model on custom images.
• SegFormer works on any input size, as it pads the input to be divisible by config.patch_sizes.
• One can use SegformerImageProcessor to prepare images and corresponding segmentation maps for the model. Note that this image processor is fairly basic and does not include all data augmentations used in the original paper. The original preprocessing pipelines (for the ADE20k dataset for instance) can be found here. The most important preprocessing step is that images and segmentation maps are randomly cropped and padded to the same size, such as 512x512 or 640x640, after which they are normalized.
• One additional thing to keep in mind is that one can initialize SegformerImageProcessor with reduce_labels set to True or False. In some datasets (like ADE20k), the 0 index is used in the annotated segmentation maps for background. However, ADE20k doesn’t include the “background” class in its 150 labels. Therefore, reduce_labels is used to reduce all labels by 1, and to make sure no loss is computed for the background class (i.e. it replaces 0 in the annotated maps by 255, which is the ignore_index of the loss function used by SegformerForSemanticSegmentation). However, other datasets use the 0 index as background class and include this class as part of all labels. In that case, reduce_labels should be set to False, as loss should also be computed for the background class.
• As most models, SegFormer comes in different sizes, the details of which can be found in the table below (taken from Table 7 of the original paper).
Model variant Depths Hidden sizes Decoder hidden size Params (M) ImageNet-1k Top 1
MiT-b0 [2, 2, 2, 2] [32, 64, 160, 256] 256 3.7 70.5
MiT-b1 [2, 2, 2, 2] [64, 128, 320, 512] 256 14.0 78.7
MiT-b2 [3, 4, 6, 3] [64, 128, 320, 512] 768 25.4 81.6
MiT-b3 [3, 4, 18, 3] [64, 128, 320, 512] 768 45.2 83.1
MiT-b4 [3, 8, 27, 3] [64, 128, 320, 512] 768 62.6 83.6
MiT-b5 [3, 6, 40, 3] [64, 128, 320, 512] 768 82.0 83.8

Note that MiT in the above table refers to the Mix Transformer encoder backbone introduced in SegFormer. For SegFormer’s results on the segmentation datasets like ADE20k, refer to the paper.

## Resources

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

Image Classification

Semantic segmentation:

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.

## SegformerConfig

### class transformers.SegformerConfig

< >

( num_channels = 3 num_encoder_blocks = 4 depths = [2, 2, 2, 2] sr_ratios = [8, 4, 2, 1] hidden_sizes = [32, 64, 160, 256] patch_sizes = [7, 3, 3, 3] strides = [4, 2, 2, 2] num_attention_heads = [1, 2, 5, 8] mlp_ratios = [4, 4, 4, 4] hidden_act = 'gelu' hidden_dropout_prob = 0.0 attention_probs_dropout_prob = 0.0 classifier_dropout_prob = 0.1 initializer_range = 0.02 drop_path_rate = 0.1 layer_norm_eps = 1e-06 decoder_hidden_size = 256 semantic_loss_ignore_index = 255 **kwargs )

Parameters

• num_channels (int, optional, defaults to 3) — The number of input channels.
• num_encoder_blocks (int, optional, defaults to 4) — The number of encoder blocks (i.e. stages in the Mix Transformer encoder).
• depths (List[int], optional, defaults to [2, 2, 2, 2]) — The number of layers in each encoder block.
• sr_ratios (List[int], optional, defaults to [8, 4, 2, 1]) — Sequence reduction ratios in each encoder block.
• hidden_sizes (List[int], optional, defaults to [32, 64, 160, 256]) — Dimension of each of the encoder blocks.
• patch_sizes (List[int], optional, defaults to [7, 3, 3, 3]) — Patch size before each encoder block.
• strides (List[int], optional, defaults to [4, 2, 2, 2]) — Stride before each encoder block.
• num_attention_heads (List[int], optional, defaults to [1, 2, 5, 8]) — Number of attention heads for each attention layer in each block of the Transformer encoder.
• mlp_ratios (List[int], optional, defaults to [4, 4, 4, 4]) — Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the encoder blocks.
• hidden_act (str or function, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.
• hidden_dropout_prob (float, optional, defaults to 0.0) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
• attention_probs_dropout_prob (float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.
• classifier_dropout_prob (float, optional, defaults to 0.1) — The dropout probability before the classification head.
• initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
• drop_path_rate (float, optional, defaults to 0.1) — The dropout probability for stochastic depth, used in the blocks of the Transformer encoder.
• layer_norm_eps (float, optional, defaults to 1e-6) — The epsilon used by the layer normalization layers.
• decoder_hidden_size (int, optional, defaults to 256) — The dimension of the all-MLP decode head.
• semantic_loss_ignore_index (int, optional, defaults to 255) — The index that is ignored by the loss function of the semantic segmentation model.

This is the configuration class to store the configuration of a SegformerModel. It is used to instantiate an SegFormer 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 SegFormer nvidia/segformer-b0-finetuned-ade-512-512 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 SegformerModel, SegformerConfig

>>> # Initializing a SegFormer nvidia/segformer-b0-finetuned-ade-512-512 style configuration
>>> configuration = SegformerConfig()

>>> # Initializing a model from the nvidia/segformer-b0-finetuned-ade-512-512 style configuration
>>> model = SegformerModel(configuration)

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

## SegformerFeatureExtractor

### class transformers.SegformerFeatureExtractor

< >

( *args **kwargs )

#### __call__

< >

( images segmentation_maps = None **kwargs )

Preprocesses a batch of images and optionally segmentation maps.

Overrides the __call__ method of the Preprocessor class so that both images and segmentation maps can be passed in as positional arguments.

#### post_process_semantic_segmentation

< >

( outputs target_sizes: typing.List[typing.Tuple] = None ) semantic_segmentation

Parameters

• outputs (SegformerForSemanticSegmentation) — Raw outputs of the model.
• target_sizes (List[Tuple] of length batch_size, optional) — List of tuples corresponding to the requested final size (height, width) of each prediction. If left to None, predictions will not be resized.

Returns

semantic_segmentation

List[torch.Tensor] of length batch_size, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if target_sizes is specified). Each entry of each torch.Tensor correspond to a semantic class id.

Converts the output of SegformerForSemanticSegmentation into semantic segmentation maps. Only supports PyTorch.

## SegformerImageProcessor

### class transformers.SegformerImageProcessor

< >

( do_resize: bool = True size: typing.Dict[str, int] = None resample: Resampling = <Resampling.BILINEAR: 2> do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_reduce_labels: bool = False **kwargs )

Parameters

• do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions to the specified (size["height"], size["width"]). Can be overridden by the do_resize parameter in the preprocess method.
• size (Dict[str, int] optional, defaults to {"height" -- 512, "width": 512}): Size of the output image after resizing. Can be overridden by the size parameter in the preprocess method.
• resample (PILImageResampling, optional, defaults to PILImageResampling.BILINEAR) — Resampling filter to use if resizing the image. Can be overridden by the resample parameter in the preprocess method.
• do_rescale (bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor. Can be overridden by the do_rescale parameter in the preprocess method.
• rescale_factor (int or float, optional, defaults to 1/255) — Whether to normalize the image. Can be overridden by the do_normalize parameter in the preprocess method.
• do_normalize (bool, optional, defaults to True) — Whether to normalize the image. Can be overridden by the do_normalize parameter in the preprocess method.
• image_mean (float or List[float], optional, defaults to IMAGENET_STANDARD_MEAN) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_mean parameter in the preprocess method.
• image_std (float or List[float], optional, defaults to IMAGENET_STANDARD_STD) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_std parameter in the preprocess method.
• do_reduce_labels (bool, optional, defaults to False) — Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255. Can be overridden by the do_reduce_labels parameter in the preprocess method.

Constructs a Segformer image processor.

#### preprocess

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] segmentation_maps: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')], NoneType] = None do_resize: typing.Optional[bool] = None size: typing.Union[typing.Dict[str, int], NoneType] = None resample: Resampling = None do_rescale: typing.Optional[bool] = None rescale_factor: typing.Optional[float] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_reduce_labels: typing.Optional[bool] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: ChannelDimension = <ChannelDimension.FIRST: 'channels_first'> **kwargs )

Parameters

• images (ImageInput) — Image to preprocess.
• segmentation_maps (ImageInput, optional) — Segmentation map to preprocess.
• do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
• size (Dict[str, int], optional, defaults to self.size) — Size of the image after resize is applied.
• resample (int, optional, defaults to self.resample) — Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling, Only has an effect if do_resize is set to True.
• do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image values between [0 - 1].
• rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True.
• do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
• image_mean (float or List[float], optional, defaults to self.image_mean) — Image mean.
• image_std (float or List[float], optional, defaults to self.image_std) — Image standard deviation.
• do_reduce_labels (bool, optional, defaults to self.do_reduce_labels) — Whether or not to reduce all label values of segmentation maps by 1. Usually used for datasets where 0 is used for background, and background itself is not included in all classes of a dataset (e.g. ADE20k). The background label will be replaced by 255.
• return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
• Unset: Return a list of np.ndarray.
• TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
• TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
• TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
• TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.
• data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
• ChannelDimension.FIRST: image in (num_channels, height, width) format.
• ChannelDimension.LAST: image in (height, width, num_channels) format.

Preprocess an image or batch of images.

#### post_process_semantic_segmentation

< >

( outputs target_sizes: typing.List[typing.Tuple] = None ) semantic_segmentation

Parameters

• outputs (SegformerForSemanticSegmentation) — Raw outputs of the model.
• target_sizes (List[Tuple] of length batch_size, optional) — List of tuples corresponding to the requested final size (height, width) of each prediction. If left to None, predictions will not be resized.

Returns

semantic_segmentation

List[torch.Tensor] of length batch_size, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if target_sizes is specified). Each entry of each torch.Tensor correspond to a semantic class id.

Converts the output of SegformerForSemanticSegmentation into semantic segmentation maps. Only supports PyTorch.

## SegformerModel

### class transformers.SegformerModel

< >

( config )

Parameters

• config (SegformerConfig) — 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.

The bare SegFormer encoder (Mix-Transformer) outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module sub-class. 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 output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) transformers.modeling_outputs.BaseModelOutput or tuple(torch.FloatTensor)

Parameters

• pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using AutoImageProcessor. See SegformerImageProcessor.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.

Returns

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

A transformers.modeling_outputs.BaseModelOutput 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 (SegformerConfig) and inputs.

• last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.

• 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, sequence_length, hidden_size).

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, sequence_length, sequence_length).

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

The SegformerModel 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.

Example:

>>> from transformers import AutoImageProcessor, SegformerModel
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("nvidia/mit-b0")
>>> model = SegformerModel.from_pretrained("nvidia/mit-b0")

>>> inputs = image_processor(image, return_tensors="pt")

...     outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 256, 16, 16]

< >

( config )

#### forward

< >

( encoder_hidden_states: FloatTensor )

## SegformerForImageClassification

### class transformers.SegformerForImageClassification

< >

( config )

Parameters

• config (SegformerConfig) — 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.

SegFormer Model transformer with an image classification head on top (a linear layer on top of the final hidden states) e.g. for ImageNet.

This model is a PyTorch torch.nn.Module sub-class. 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: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) transformers.models.segformer.modeling_segformer.SegFormerImageClassifierOutput or tuple(torch.FloatTensor)

Parameters

• pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using AutoImageProcessor. See SegformerImageProcessor.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,), optional) — Labels for computing the image classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Returns

transformers.models.segformer.modeling_segformer.SegFormerImageClassifierOutput or tuple(torch.FloatTensor)

A transformers.models.segformer.modeling_segformer.SegFormerImageClassifierOutput 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 (SegformerConfig) and inputs.

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

• logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).

• 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 stage) of shape (batch_size, num_channels, height, width). Hidden-states (also called feature maps) of the model at the output of each stage.

• 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 SegformerForImageClassification 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.

Example:

>>> from transformers import AutoImageProcessor, SegformerForImageClassification
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("nvidia/mit-b0")
>>> model = SegformerForImageClassification.from_pretrained("nvidia/mit-b0")

>>> inputs = image_processor(image, return_tensors="pt")

...     logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
tabby, tabby cat

## SegformerForSemanticSegmentation

### class transformers.SegformerForSemanticSegmentation

< >

( config )

Parameters

• config (SegformerConfig) — 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.

SegFormer Model transformer with an all-MLP decode head on top e.g. for ADE20k, CityScapes. This model is a PyTorch torch.nn.Module sub-class. 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: typing.Optional[torch.LongTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) transformers.modeling_outputs.SemanticSegmenterOutput or tuple(torch.FloatTensor)

Parameters

• pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using AutoImageProcessor. See SegformerImageProcessor.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 semantic segmentation maps for computing the loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels > 1, a classification loss is computed (Cross-Entropy).

Returns

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

A transformers.modeling_outputs.SemanticSegmenterOutput 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 (SegformerConfig) and inputs.

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

• logits (torch.FloatTensor of shape (batch_size, config.num_labels, logits_height, logits_width)) — Classification scores for each pixel.

The logits returned do not necessarily have the same size as the pixel_values passed as inputs. This is to avoid doing two interpolations and lose some quality when a user needs to resize the logits to the original image size as post-processing. You should always check your logits shape and resize as needed.

• 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, patch_size, hidden_size).

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 SegformerForSemanticSegmentation 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, SegformerForSemanticSegmentation
>>> from PIL import Image
>>> import requests

>>> image_processor = AutoImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
>>> model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")

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

>>> inputs = image_processor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)
>>> list(logits.shape)
[1, 150, 128, 128]

< >

( *args **kwargs )

#### call

< >

( encoder_hidden_states training: bool = False )

## TFSegformerModel

### class transformers.TFSegformerModel

< >

( *args **kwargs )

Parameters

• config (SegformerConfig) — 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.

The bare SegFormer encoder (Mix-Transformer) outputting raw hidden-states without any specific head on top. This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: Tensor output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None training: bool = False ) transformers.modeling_tf_outputs.TFBaseModelOutput or tuple(tf.Tensor)

Parameters

• pixel_values (np.ndarray, tf.Tensor, List[tf.Tensor] Dict[str, tf.Tensor] or Dict[str, np.ndarray] and each example must have the shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See SegformerImageProcessor.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. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• 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. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False“) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

transformers.modeling_tf_outputs.TFBaseModelOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFBaseModelOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (SegformerConfig) and inputs.

• last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.

• hidden_states (tuple(tf.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

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

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

The TFSegformerModel 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.

Example:

>>> from transformers import AutoImageProcessor, TFSegformerModel
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("nvidia/mit-b0")
>>> model = TFSegformerModel.from_pretrained("nvidia/mit-b0")

>>> inputs = image_processor(image, return_tensors="tf")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 256, 16, 16]

## TFSegformerForImageClassification

### class transformers.TFSegformerForImageClassification

< >

( *args **kwargs )

Parameters

• config (SegformerConfig) — 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.

SegFormer Model transformer with an image classification head on top (a linear layer on top of the final hidden states) e.g. for ImageNet.

This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: typing.Optional[tensorflow.python.framework.ops.Tensor] = None labels: typing.Optional[tensorflow.python.framework.ops.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) transformers.modeling_tf_outputs.TFSequenceClassifierOutput or tuple(tf.Tensor)

Parameters

• pixel_values (np.ndarray, tf.Tensor, List[tf.Tensor] Dict[str, tf.Tensor] or Dict[str, np.ndarray] and each example must have the shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See SegformerImageProcessor.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. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• 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. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False“) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).

Returns

transformers.modeling_tf_outputs.TFSequenceClassifierOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFSequenceClassifierOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (SegformerConfig) and inputs.

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

• logits (tf.Tensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

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

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

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

The TFSegformerForImageClassification 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.

Example:

>>> from transformers import AutoImageProcessor, TFSegformerForImageClassification
>>> import tensorflow as tf
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("nvidia/mit-b0")
>>> model = TFSegformerForImageClassification.from_pretrained("nvidia/mit-b0")

>>> inputs = image_processor(image, return_tensors="tf")
>>> logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = int(tf.math.argmax(logits, axis=-1))
>>> print(model.config.id2label[predicted_label])
tabby, tabby cat

## TFSegformerForSemanticSegmentation

### class transformers.TFSegformerForSemanticSegmentation

< >

( *args **kwargs )

Parameters

• config (SegformerConfig) — 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.

SegFormer Model transformer with an all-MLP decode head on top e.g. for ADE20k, CityScapes. This model inherits from TFPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: Tensor labels: typing.Optional[tensorflow.python.framework.ops.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) transformers.modeling_tf_outputs.TFSemanticSegmenterOutput or tuple(tf.Tensor)

Parameters

• pixel_values (np.ndarray, tf.Tensor, List[tf.Tensor] Dict[str, tf.Tensor] or Dict[str, np.ndarray] and each example must have the shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See SegformerImageProcessor.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. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• 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. This argument can be used only in eager mode, in graph mode the value in the config will be used instead.
• return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set to True.
• training (bool, optional, defaults to False“) — Whether or not to use the model in training mode (some modules like dropout modules have different behaviors between training and evaluation).
• labels (tf.Tensor of shape (batch_size, height, width), optional) — Ground truth semantic segmentation maps for computing the loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels > 1, a (per-pixel) classification loss is computed (Cross-Entropy).

Returns

transformers.modeling_tf_outputs.TFSemanticSegmenterOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFSemanticSegmenterOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (SegformerConfig) and inputs.

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

• logits (tf.Tensor of shape (batch_size, config.num_labels, logits_height, logits_width)) — Classification scores for each pixel.

The logits returned do not necessarily have the same size as the pixel_values passed as inputs. This is to avoid doing two interpolations and lose some quality when a user needs to resize the logits to the original image size as post-processing. You should always check your logits shape and resize as needed.

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (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, patch_size, hidden_size).

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

• attentions (tuple(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of tf.Tensor (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 TFSegformerForSemanticSegmentation 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, TFSegformerForSemanticSegmentation
>>> 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("nvidia/segformer-b0-finetuned-ade-512-512")
>>> model = TFSegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")

>>> inputs = image_processor(images=image, return_tensors="tf")
>>> outputs = model(**inputs, training=False)
>>> # logits are of shape (batch_size, num_labels, height/4, width/4)
>>> logits = outputs.logits
>>> list(logits.shape)
[1, 150, 128, 128]