transformers/main/en/model_doc/bit.md

# Big Transfer (BiT)

## Overview

The BiT model was proposed in [Big Transfer (BiT): General Visual Representation Learning](https://huggingface.co/papers/1912.11370) by Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby.
BiT is a simple recipe for scaling up pre-training of [ResNet](resnet)-like architectures (specifically, ResNetv2). The method results in significant improvements for transfer learning.

The abstract from the paper is the following:

*Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task. We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT). By combining a few carefully selected components, and transferring using a simple heuristic, we achieve strong performance on over 20 datasets. BiT performs well across a surprisingly wide range of data regimes -- from 1 example per class to 1M total examples. BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB). On small datasets, BiT attains 76.8% on ILSVRC-2012 with 10 examples per class, and 97.0% on CIFAR-10 with 10 examples per class. We conduct detailed analysis of the main components that lead to high transfer performance.*

This model was contributed by [nielsr](https://huggingface.co/nielsr).
The original code can be found [here](https://github.com/google-research/big_transfer).

## Usage tips

- BiT models are equivalent to ResNetv2 in terms of architecture, except that: 1) all batch normalization layers are replaced by [group normalization](https://huggingface.co/papers/1803.08494),

2) [weight standardization](https://huggingface.co/papers/1903.10520) is used for convolutional layers. The authors show that the combination of both is useful for training with large batch sizes, and has a significant
impact on transfer learning.

## Resources

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

- [BitForImageClassification](/docs/transformers/main/en/model_doc/bit#transformers.BitForImageClassification) 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)

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.

## BitConfig[[transformers.BitConfig]]

#### transformers.BitConfig[[transformers.BitConfig]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/configuration_bit.py#L25)

This is the configuration class to store the configuration of a BitModel. It is used to instantiate a Bit
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 [google/bit-50](https://huggingface.co/google/bit-50)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:
```python
>>> from transformers import BitConfig, BitModel

>>> # Initializing a BiT bit-50 style configuration
>>> configuration = BitConfig()

>>> # Initializing a model (with random weights) from the bit-50 style configuration
>>> model = BitModel(configuration)

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

**Parameters:**

num_channels (`int`, *optional*, defaults to `3`) : The number of input channels.

embedding_size (`int`, *optional*, defaults to `64`) : Dimensionality of the embeddings and hidden states.

hidden_sizes (`Union[list[int], tuple[int, ...]]`, *optional*, defaults to `(256, 512, 1024, 2048)`) : Dimensionality (hidden size) at each stage of the model.

depths (`Union[list[int], tuple[int, ...]]`, *optional*, defaults to `(3, 4, 6, 3)`) : Depth of each layer in the Transformer.

layer_type (`str`, *optional*, defaults to `"preactivation"`) : The layer to use, it can be either `"preactivation"` or `"bottleneck"`.

hidden_act (`str`, *optional*, defaults to `relu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

global_padding (`str`, *optional*) : Padding strategy to use for the convolutional layers. Can be either `"valid"`, `"same"`, or `None`.

num_groups (`int`, *optional*, defaults to 32) : Number of groups used for the `BitGroupNormActivation` layers.

drop_path_rate (`Union[float, int]`, *optional*, defaults to `0.0`) : Drop path rate for the patch fusion.

embedding_dynamic_padding (`bool`, *optional*, defaults to `False`) : Whether or not to make use of dynamic padding for the embedding layer.

output_stride (`int`, *optional*, defaults to `32`) : The ratio between the spatial resolution of the input and output feature maps.

width_factor (`int`, *optional*, defaults to 1) : The width factor for the model.

## BitImageProcessor[[transformers.BitImageProcessor]]

#### transformers.BitImageProcessor[[transformers.BitImageProcessor]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/image_processing_bit.py#L22)

Constructs a BitImageProcessor image processor.

preprocesstransformers.BitImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/main/src/transformers/image_processing_utils.py#L382[{"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": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **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`.
- **return_tensors** (`str` or [TensorType](/docs/transformers/main/en/internal/file_utils#transformers.TensorType), *optional*) --
  Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors.
- ****kwargs** ([ImagesKwargs](/docs/transformers/main/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:**

- ****kwargs** ([ImagesKwargs](/docs/transformers/main/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.

## BitImageProcessorPil[[transformers.BitImageProcessorPil]]

#### transformers.BitImageProcessorPil[[transformers.BitImageProcessorPil]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/image_processing_pil_bit.py#L22)

Constructs a BitImageProcessor image processor.

preprocesstransformers.BitImageProcessorPil.preprocesshttps://github.com/huggingface/transformers/blob/main/src/transformers/image_processing_utils.py#L382[{"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": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **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`.
- **return_tensors** (`str` or [TensorType](/docs/transformers/main/en/internal/file_utils#transformers.TensorType), *optional*) --
  Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors.
- ****kwargs** ([ImagesKwargs](/docs/transformers/main/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:**

- ****kwargs** ([ImagesKwargs](/docs/transformers/main/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.

## BitModel[[transformers.BitModel]]

#### transformers.BitModel[[transformers.BitModel]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/modeling_bit.py#L646)

The bare Bit Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.BitModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/modeling_bit.py#L664[{"name": "pixel_values", "val": ": Tensor"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"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
  [BitImageProcessor](/docs/transformers/main/en/model_doc/bit#transformers.BitImageProcessor). See `BitImageProcessor.__call__()` for details (`processor_class` uses
  [BitImageProcessor](/docs/transformers/main/en/model_doc/bit#transformers.BitImageProcessor) for processing images).
- **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](/docs/transformers/main/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`BaseModelOutputWithPoolingAndNoAttention` or `tuple(torch.FloatTensor)`A `BaseModelOutputWithPoolingAndNoAttention` 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 ([BitConfig](/docs/transformers/main/en/model_doc/bit#transformers.BitConfig)) and inputs.
The [BitModel](/docs/transformers/main/en/model_doc/bit#transformers.BitModel) 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, num_channels, height, width)`) -- 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 after a pooling operation on the spatial dimensions.
- **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, num_channels, height, width)`.

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

Example:

```python
```

**Parameters:**

config ([BitModel](/docs/transformers/main/en/model_doc/bit#transformers.BitModel)) : 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/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

``BaseModelOutputWithPoolingAndNoAttention` or `tuple(torch.FloatTensor)``

A `BaseModelOutputWithPoolingAndNoAttention` 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 ([BitConfig](/docs/transformers/main/en/model_doc/bit#transformers.BitConfig)) and inputs.

## BitForImageClassification[[transformers.BitForImageClassification]]

#### transformers.BitForImageClassification[[transformers.BitForImageClassification]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/modeling_bit.py#L705)

BiT Model with an image classification head on top (a linear layer on top of the pooled features), e.g. for
ImageNet.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.BitForImageClassification.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/bit/modeling_bit.py#L718[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) --
  The tensors corresponding to the input images. Pixel values can be obtained using
  [BitImageProcessor](/docs/transformers/main/en/model_doc/bit#transformers.BitImageProcessor). See `BitImageProcessor.__call__()` for details (`processor_class` uses
  [BitImageProcessor](/docs/transformers/main/en/model_doc/bit#transformers.BitImageProcessor) 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 classification loss is computed (Cross-Entropy).
- **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](/docs/transformers/main/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ImageClassifierOutputWithNoAttention](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)`A [ImageClassifierOutputWithNoAttention](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) 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 ([BitConfig](/docs/transformers/main/en/model_doc/bit#transformers.BitConfig)) and inputs.
The [BitForImageClassification](/docs/transformers/main/en/model_doc/bit#transformers.BitForImageClassification) 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, num_channels, height, width)`. Hidden-states (also
  called feature maps) of the model at the output of each stage.

Example:

```python
>>> from transformers import AutoImageProcessor, BitForImageClassification
>>> import torch
>>> from datasets import load_dataset

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

>>> image_processor = AutoImageProcessor.from_pretrained("google/bit-50")
>>> model = BitForImageClassification.from_pretrained("google/bit-50")

>>> 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 ([BitForImageClassification](/docs/transformers/main/en/model_doc/bit#transformers.BitForImageClassification)) : 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/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ImageClassifierOutputWithNoAttention](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)``

A [ImageClassifierOutputWithNoAttention](/docs/transformers/main/en/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) 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 ([BitConfig](/docs/transformers/main/en/model_doc/bit#transformers.BitConfig)) and inputs.