# BEiT ## Overview The BEiT model was proposed in [BEiT: BERT Pre-Training of Image Transformers](https://huggingface.co/papers/2106.08254) by Hangbo Bao, Li Dong and Furu Wei. Inspired by BERT, BEiT is the first paper that makes self-supervised pre-training of Vision Transformers (ViTs) outperform supervised pre-training. Rather than pre-training the model to predict the class of an image (as done in the [original ViT paper](https://huggingface.co/papers/2010.11929)), BEiT models are pre-trained to predict visual tokens from the codebook of OpenAI's [DALL-E model](https://huggingface.co/papers/2102.12092) given masked patches. The abstract from the paper is the following: *We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%).* This model was contributed by [nielsr](https://huggingface.co/nielsr). The original code can be found [here](https://github.com/microsoft/unilm/tree/master/beit). ## Usage tips - BEiT models are regular Vision Transformers, but pre-trained in a self-supervised way rather than supervised. They outperform both the [original model (ViT)](vit) as well as [Data-efficient Image Transformers (DeiT)](deit) when fine-tuned on ImageNet-1K and CIFAR-100. You can check out demo notebooks regarding inference as well as fine-tuning on custom data [here](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/VisionTransformer) (you can just replace [ViTImageProcessor](/docs/transformers/v5.8.0/en/model_doc/vit#transformers.ViTImageProcessor) by [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor) and [ViTForImageClassification](/docs/transformers/v5.8.0/en/model_doc/vit#transformers.ViTForImageClassification) by [BeitForImageClassification](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForImageClassification)). - There's also a demo notebook available which showcases how to combine DALL-E's image tokenizer with BEiT for performing masked image modeling. You can find it [here](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/BEiT). - As the BEiT models expect each image to be of the same size (resolution), one can use [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor) to resize (or rescale) and normalize images for the model. - Both the patch resolution and image resolution used during pre-training or fine-tuning are reflected in the name of each checkpoint. For example, `microsoft/beit-base-patch16-224` refers to a base-sized architecture with patch resolution of 16x16 and fine-tuning resolution of 224x224. All checkpoints can be found on the [hub](https://huggingface.co/models?search=microsoft/beit). - The available checkpoints are either (1) pre-trained on [ImageNet-22k](http://www.image-net.org/) (a collection of 14 million images and 22k classes) only, (2) also fine-tuned on ImageNet-22k or (3) also fine-tuned on [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/) (also referred to as ILSVRC 2012, a collection of 1.3 million images and 1,000 classes). - BEiT uses relative position embeddings, inspired by the T5 model. During pre-training, the authors shared the relative position bias among the several self-attention layers. During fine-tuning, each layer's relative position bias is initialized with the shared relative position bias obtained after pre-training. Note that, if one wants to pre-train a model from scratch, one needs to either set the `use_relative_position_bias` or the `use_relative_position_bias` attribute of [BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig) to `True` in order to add position embeddings. drawing BEiT pre-training. Taken from the original paper. ### Using Scaled Dot Product Attention (SDPA) PyTorch includes a native scaled dot-product attention (SDPA) operator as part of `torch.nn.functional`. This function encompasses several implementations that can be applied depending on the inputs and the hardware in use. See the [official documentation](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) or the [GPU Inference](https://huggingface.co/docs/transformers/main/en/perf_infer_gpu_one#pytorch-scaled-dot-product-attention) page for more information. SDPA is used by default for `torch>=2.1.1` when an implementation is available, but you may also set `attn_implementation="sdpa"` in `from_pretrained()` to explicitly request SDPA to be used. ```python from transformers import BeitForImageClassification model = BeitForImageClassification.from_pretrained("microsoft/beit-base-patch16-224", attn_implementation="sdpa", device_map="auto") ... ``` For the best speedups, we recommend loading the model in half-precision (e.g. `torch.float16` or `torch.bfloat16`). On a local benchmark (NVIDIA GeForce RTX 2060-8GB, PyTorch 2.5.1, OS Ubuntu 20.04) with `float16` and `microsoft/beit-base-patch16-224` model, we saw the following improvements during training and inference: #### Training | num_training_steps | batch_size | image_size | is_cuda | Time per batch (eager - s) | Time per batch (sdpa - s) | Speedup (%) | Eager peak mem (MB) | SDPA peak mem (MB) | Mem saving (%) | |--------------------|------------|--------------|---------|----------------------------|---------------------------|-------------|----------------------|--------------------|----------------| | 50 | 2 | (1048, 640) | True | 0.984 | 0.746 | 31.975 | 6738.915 | 4319.886 | 55.998 | #### Inference | Image batch size | Eager (s/iter) | Eager CI, % | Eager memory (MB) | SDPA (s/iter) | SDPA CI, % | SDPA memory (MB) | SDPA speedup | SDPA memory saved (%) | |-------------------:|-----------------:|:--------------|--------------------:|----------------:|:-------------|-------------------:|---------------:|----------------------:| | 1 | 0.012 | ±0.3% | 3.76657e+08 | 0.011 | ±0.5% | 3.75739e+08 | 1.05 | 0.244 | | 4 | 0.013 | ±0.1% | 4.03147e+08 | 0.011 | ±0.2% | 3.90554e+08 | 1.178 | 3.225 | | 16 | 0.045 | ±0.1% | 4.96697e+08 | 0.035 | ±0.1% | 4.51232e+08 | 1.304 | 10.076 | | 32 | 0.088 | ±0.1% | 6.24417e+08 | 0.066 | ±0.1% | 5.33488e+08 | 1.325 | 17.044 | ## Resources A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with BEiT. - [BeitForImageClassification](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForImageClassification) is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/image-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb). - See also: [Image classification task guide](../tasks/image_classification) **Semantic segmentation** - [Semantic segmentation task guide](../tasks/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. ## BEiT specific outputs[[transformers.models.beit.modeling_beit.BeitModelOutputWithPooling]] #### transformers.models.beit.modeling_beit.BeitModelOutputWithPooling[[transformers.models.beit.modeling_beit.BeitModelOutputWithPooling]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L52) Class for outputs of [BeitModel](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitModel). **Parameters:** last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) : Sequence of hidden-states at the output of the last layer of the model. pooler_output (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) : Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. 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. ## BeitConfig[[transformers.BeitConfig]] #### transformers.BeitConfig[[transformers.BeitConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/configuration_beit.py#L25) This is the configuration class to store the configuration of a BeitModel. It is used to instantiate a Beit 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 [microsoft/beit-base-patch16-224-pt22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import BeitConfig, BeitModel >>> # Initializing a BEiT beit-base-patch16-224-pt22k style configuration >>> configuration = BeitConfig() >>> # Initializing a model (with random weights) from the beit-base-patch16-224-pt22k style configuration >>> model = BeitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** vocab_size (`int`, *optional*, defaults to `8192`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. hidden_size (`int`, *optional*, defaults to `768`) : Dimension of the hidden representations. num_hidden_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder. intermediate_size (`int`, *optional*, defaults to `3072`) : Dimension of the MLP representations. hidden_act (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. hidden_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to `1e-12`) : The epsilon used by the layer normalization layers. image_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `224`) : The size (resolution) of each image. patch_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `16`) : The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to `3`) : The number of input channels. use_mask_token (`bool`, *optional*, defaults to `False`) : Whether to use a mask token for masked image modeling. use_absolute_position_embeddings (`bool`, *optional*, defaults to `False`) : Whether to use absolute position embeddings. use_relative_position_bias (`bool`, *optional*, defaults to `False`) : Whether to use T5-style relative position embeddings in the self-attention layers. use_shared_relative_position_bias (`bool`, *optional*, defaults to `False`) : Whether to use the same relative position embeddings across all self-attention layers of the Transformer. layer_scale_init_value (`float`, *optional*, defaults to `0.1`) : Scale to use in the self-attention layers. 0.1 for base, 1e-6 for large. Set 0 to disable layer scale. drop_path_rate (`Union[float, int]`, *optional*, defaults to `0.1`) : Drop path rate for the patch fusion. use_mean_pooling (`bool`, *optional*, defaults to `True`) : Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the CLS token, before applying the classification head. pool_scales (`tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`) : Pooling scales used in Pooling Pyramid Module applied on the last feature map. use_auxiliary_head (`bool`, *optional*, defaults to `True`) : Whether to use an auxiliary head during training. auxiliary_loss_weight (`float`, *optional*, defaults to 0.4) : Weight of the cross-entropy loss of the auxiliary head. auxiliary_channels (`int`, *optional*, defaults to 256) : Number of channels to use in the auxiliary head. auxiliary_num_convs (`int`, *optional*, defaults to 1) : Number of convolutional layers to use in the auxiliary head. auxiliary_concat_input (`bool`, *optional*, defaults to `False`) : Whether to concatenate the output of the auxiliary head with the input before the classification layer. semantic_loss_ignore_index (`int`, *optional*, defaults to `255`) : The index that is ignored by the loss function of the semantic segmentation model. add_fpn (`bool`, *optional*, defaults to `False`) : Whether to add a FPN as part of the backbone. Only relevant for `BeitBackbone`. reshape_hidden_states (`bool`, *optional*, defaults to `True`) : Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size, seq_len, hidden_size)`. Only relevant for `BeitBackbone`. ## BeitImageProcessor[[transformers.BeitImageProcessor]] #### transformers.BeitImageProcessor[[transformers.BeitImageProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/image_processing_beit.py#L49) Constructs a BeitImageProcessor image processor. preprocesstransformers.BeitImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/image_processing_beit.py#L69[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "segmentation_maps", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.beit.image_processing_beit.BeitImageProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **segmentation_maps** (`ImageInput`, *optional*) -- The segmentation maps to preprocess. - **do_reduce_labels** (`bool`, *kwargs*, *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](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** do_reduce_labels (`bool`, *kwargs*, *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. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. #### post_process_semantic_segmentation[[transformers.BeitImageProcessor.post_process_semantic_segmentation]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/image_processing_beit.py#L182) Converts the output of [BeitForSemanticSegmentation](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForSemanticSegmentation) into semantic segmentation maps. **Parameters:** outputs ([BeitForSemanticSegmentation](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForSemanticSegmentation)) : 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 unset, 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. ## BeitImageProcessorPil[[transformers.BeitImageProcessorPil]] #### transformers.BeitImageProcessorPil[[transformers.BeitImageProcessorPil]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/image_processing_pil_beit.py#L46) Constructs a BeitImageProcessor image processor. preprocesstransformers.BeitImageProcessorPil.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/image_processing_pil_beit.py#L66[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "segmentation_maps", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.beit.image_processing_pil_beit.BeitImageProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **segmentation_maps** (`ImageInput`, *optional*) -- The segmentation maps to preprocess. - **do_reduce_labels** (`bool`, *kwargs*, *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](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** do_reduce_labels (`bool`, *kwargs*, *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. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. #### post_process_semantic_segmentation[[transformers.BeitImageProcessorPil.post_process_semantic_segmentation]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/image_processing_pil_beit.py#L162) Converts the output of [BeitForSemanticSegmentation](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForSemanticSegmentation) into semantic segmentation maps. **Parameters:** outputs ([BeitForSemanticSegmentation](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForSemanticSegmentation)) : 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 unset, 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. ## BeitModel[[transformers.BeitModel]] #### transformers.BeitModel[[transformers.BeitModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L674) The bare Beit Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). 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 PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BeitModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L697[{"name": "pixel_values", "val": ": Tensor"}, {"name": "bool_masked_pos", "val": ": torch.BoolTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)`) -- The tensors corresponding to the input images. Pixel values can be obtained using [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor). See `BeitImageProcessor.__call__()` for details (`processor_class` uses [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor) for processing images). - **bool_masked_pos** (`torch.BoolTensor` of shape `(batch_size, num_patches)`, *optional*) -- Boolean masked positions. Indicates which patches are masked (1) and which aren't (0). - **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. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[BeitModelOutputWithPooling](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.models.beit.modeling_beit.BeitModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [BeitModelOutputWithPooling](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.models.beit.modeling_beit.BeitModelOutputWithPooling) 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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. The [BeitModel](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitModel) 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. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. - **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. Example: ```python ``` **Parameters:** config ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) : 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()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. add_pooling_layer (`bool`, *optional*, defaults to `True`) : Whether to add a pooling layer **Returns:** `[BeitModelOutputWithPooling](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.models.beit.modeling_beit.BeitModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BeitModelOutputWithPooling](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.models.beit.modeling_beit.BeitModelOutputWithPooling) 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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. ## BeitForMaskedImageModeling[[transformers.BeitForMaskedImageModeling]] #### transformers.BeitForMaskedImageModeling[[transformers.BeitForMaskedImageModeling]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L772) Beit Model transformer with a 'language' modeling head on top. BEiT does masked image modeling by predicting visual tokens of a Vector-Quantize Variational Autoencoder (VQ-VAE), whereas other vision models like ViT and DeiT predict RGB pixel values. As a result, this class is incompatible with [AutoModelForMaskedImageModeling](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoModelForMaskedImageModeling), so you will need to use [BeitForMaskedImageModeling](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForMaskedImageModeling) directly if you wish to do masked image modeling with BEiT. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). 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 PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BeitForMaskedImageModeling.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L789[{"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "bool_masked_pos", "val": ": torch.BoolTensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor). See `BeitImageProcessor.__call__()` for details (`processor_class` uses [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor) for processing images). - **bool_masked_pos** (`torch.BoolTensor` of shape `(batch_size, num_patches)`) -- Boolean masked positions. Indicates which patches are masked (1) and which aren't (0). - **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). - **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. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[MaskedLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`A [MaskedLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. The [BeitForMaskedImageModeling](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForMaskedImageModeling) 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. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Masked language modeling (MLM) loss. - **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token 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 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. Examples: ```python >>> from transformers import AutoImageProcessor, BeitForMaskedImageModeling >>> import torch >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> image_processor = AutoImageProcessor.from_pretrained("microsoft/beit-base-patch16-224-pt22k") >>> model = BeitForMaskedImageModeling.from_pretrained("microsoft/beit-base-patch16-224-pt22k") >>> num_patches = (model.config.image_size // model.config.patch_size) ** 2 >>> pixel_values = image_processor(images=image, return_tensors="pt").pixel_values >>> # create random boolean mask of shape (batch_size, num_patches) >>> bool_masked_pos = torch.randint(low=0, high=2, size=(1, num_patches)).bool() >>> outputs = model(pixel_values, bool_masked_pos=bool_masked_pos) >>> loss, logits = outputs.loss, outputs.logits >>> list(logits.shape) [1, 196, 8192] ``` **Parameters:** config ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) : 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()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[MaskedLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) or `tuple(torch.FloatTensor)`` A [MaskedLMOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.MaskedLMOutput) 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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. ## BeitForImageClassification[[transformers.BeitForImageClassification]] #### transformers.BeitForImageClassification[[transformers.BeitForImageClassification]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L873) Beit Model transformer with an image classification head on top (a linear layer on top of the average of the final hidden states of the patch tokens) e.g. for ImageNet. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). 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 PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BeitForImageClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L886[{"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor). See `BeitImageProcessor.__call__()` for details (`processor_class` uses [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor) for processing images). - **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). - **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. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ImageClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) or `tuple(torch.FloatTensor)`A [ImageClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) 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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. The [BeitForImageClassification](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForImageClassification) 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. - **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, sequence_length, hidden_size)`. 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. Example: ```python >>> from transformers import AutoImageProcessor, BeitForImageClassification >>> import torch >>> from datasets import load_dataset >>> dataset = load_dataset("huggingface/cats-image") >>> image = dataset["test"]["image"][0] >>> image_processor = AutoImageProcessor.from_pretrained("microsoft/beit-base-patch16-224-pt22k") >>> model = BeitForImageClassification.from_pretrained("microsoft/beit-base-patch16-224-pt22k") >>> inputs = image_processor(image, return_tensors="pt") >>> with torch.no_grad(): ... logits = model(**inputs).logits >>> # model predicts one of the 1000 ImageNet classes >>> predicted_label = logits.argmax(-1).item() >>> print(model.config.id2label[predicted_label]) ... ``` **Parameters:** config ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) : 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()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[ImageClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) or `tuple(torch.FloatTensor)`` A [ImageClassifierOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutput) 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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. ## BeitForSemanticSegmentation[[transformers.BeitForSemanticSegmentation]] #### transformers.BeitForSemanticSegmentation[[transformers.BeitForSemanticSegmentation]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L1168) The Beit Model with a semantic segmentation head on top e.g. for ADE20K, CityScapes. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). 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 PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.BeitForSemanticSegmentation.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/beit/modeling_beit.py#L1220[{"name": "pixel_values", "val": ": torch.Tensor | None = None"}, {"name": "labels", "val": ": torch.Tensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.Tensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor). See `BeitImageProcessor.__call__()` for details (`processor_class` uses [BeitImageProcessor](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitImageProcessor) for processing images). - **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). - **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. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[SemanticSegmenterOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.SemanticSegmenterOutput) or `tuple(torch.FloatTensor)`A [SemanticSegmenterOutput](/docs/transformers/v5.8.0/en/main_classes/output#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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs. The [BeitForSemanticSegmentation](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitForSemanticSegmentation) 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. - **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. Examples: ```python >>> from transformers import AutoImageProcessor, BeitForSemanticSegmentation >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> image_processor = AutoImageProcessor.from_pretrained("microsoft/beit-base-finetuned-ade-640-640") >>> model = BeitForSemanticSegmentation.from_pretrained("microsoft/beit-base-finetuned-ade-640-640") >>> inputs = image_processor(images=image, return_tensors="pt") >>> outputs = model(**inputs) >>> # logits are of shape (batch_size, num_labels, height, width) >>> logits = outputs.logits ``` **Parameters:** config ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) : 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()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[SemanticSegmenterOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.modeling_outputs.SemanticSegmenterOutput) or `tuple(torch.FloatTensor)`` A [SemanticSegmenterOutput](/docs/transformers/v5.8.0/en/main_classes/output#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 ([BeitConfig](/docs/transformers/v5.8.0/en/model_doc/beit#transformers.BeitConfig)) and inputs.