# Big Transfer (BiT)

## Overview

BiT モデルは、Alexander Kolesnikov、Lucas Beyer、Xiaohua Zhai、Joan Puigcerver、Jessica Yung、Sylvain Gelly によって [Big Transfer (BiT): General Visual Representation Learning](https://huggingface.co/papers/1912.11370) で提案されました。ニール・ホールズビー。
BiT は、[ResNet](resnet) のようなアーキテクチャ (具体的には ResNetv2) の事前トレーニングをスケールアップするための簡単なレシピです。この方法により、転移学習が大幅に改善されます。

論文の要約は次のとおりです。

*事前トレーニングされた表現の転送により、サンプル効率が向上し、視覚用のディープ ニューラル ネットワークをトレーニングする際のハイパーパラメーター調整が簡素化されます。大規模な教師ありデータセットでの事前トレーニングと、ターゲット タスクでのモデルの微調整のパラダイムを再検討します。私たちは事前トレーニングをスケールアップし、Big Transfer (BiT) と呼ぶシンプルなレシピを提案します。いくつかの慎重に選択されたコンポーネントを組み合わせ、シンプルなヒューリスティックを使用して転送することにより、20 を超えるデータセットで優れたパフォーマンスを実現します。 BiT は、クラスごとに 1 つのサンプルから合計 100 万のサンプルまで、驚くほど広範囲のデータ領域にわたって良好にパフォーマンスを発揮します。 BiT は、ILSVRC-2012 で 87.5%、CIFAR-10 で 99.4%、19 タスクの Visual Task Adaptation Benchmark (VTAB) で 76.3% のトップ 1 精度を達成しました。小規模なデータセットでは、BiT は ILSVRC-2012 (クラスあたり 10 例) で 76.8%、CIFAR-10 (クラスあたり 10 例) で 97.0% を達成しました。高い転写性能を実現する主要成分を詳細に分析※。

## Usage tips

- BiT モデルは、アーキテクチャの点で ResNetv2 と同等ですが、次の点が異なります: 1) すべてのバッチ正規化層が [グループ正規化](https://huggingface.co/papers/1803.08494) に置き換えられます。
2) [重みの標準化](https://huggingface.co/papers/1903.10520) は畳み込み層に使用されます。著者らは、両方の組み合わせが大きなバッチサイズでのトレーニングに役立ち、重要な効果があることを示しています。
転移学習への影響。

このモデルは、[nielsr](https://huggingface.co/nielsr) によって提供されました。
元のコードは [こちら](https://github.com/google-research/big_transfer) にあります。

## Resources

BiT を始めるのに役立つ公式 Hugging Face およびコミュニティ (🌎 で示されている) リソースのリスト。

- [BitForImageClassification](/docs/transformers/v5.8.0/ja/model_doc/bit#transformers.BitForImageClassification) は、この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/pytorch/image-classification) および [ノートブック](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb)。
- 参照: [画像分類タスク ガイド](../tasks/image_classification)

ここに含めるリソースの送信に興味がある場合は、お気軽にプル リクエストを開いてください。審査させていただきます。リソースは、既存のリソースを複製するのではなく、何か新しいものを示すことが理想的です。

## BitConfig[[transformers.BitConfig]]

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

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/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/v5.8.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/ja/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/v5.8.0/src/transformers/models/bit/image_processing_bit.py#L22)

Constructs a BitImageProcessor image processor.

preprocesstransformers.BitImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/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/v5.8.0/ja/internal/file_utils#transformers.TensorType), *optional*) --
  Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors.
- ****kwargs** (`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`, *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/v5.8.0/src/transformers/models/bit/image_processing_pil_bit.py#L22)

Constructs a BitImageProcessor image processor.

preprocesstransformers.BitImageProcessorPil.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/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/v5.8.0/ja/internal/file_utils#transformers.TensorType), *optional*) --
  Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors.
- ****kwargs** (`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`, *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/v5.8.0/src/transformers/models/bit/modeling_bit.py#L652)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/ja/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/v5.8.0/src/transformers/models/bit/modeling_bit.py#L670[{"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/v5.8.0/ja/model_doc/bit#transformers.BitImageProcessor). See `BitImageProcessor.__call__()` for details (`processor_class` uses
  [BitImageProcessor](/docs/transformers/v5.8.0/ja/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/v5.8.0/ja/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/v5.8.0/ja/model_doc/bit#transformers.BitConfig)) and inputs.
The [BitModel](/docs/transformers/v5.8.0/ja/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/v5.8.0/ja/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/v5.8.0/ja/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/v5.8.0/ja/model_doc/bit#transformers.BitConfig)) and inputs.

## BitForImageClassification[[transformers.BitForImageClassification]]

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

[Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/bit/modeling_bit.py#L711)

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/v5.8.0/ja/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/v5.8.0/src/transformers/models/bit/modeling_bit.py#L724[{"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/v5.8.0/ja/model_doc/bit#transformers.BitImageProcessor). See `BitImageProcessor.__call__()` for details (`processor_class` uses
  [BitImageProcessor](/docs/transformers/v5.8.0/ja/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/v5.8.0/ja/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[ImageClassifierOutputWithNoAttention](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)`A [ImageClassifierOutputWithNoAttention](/docs/transformers/v5.8.0/ja/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/v5.8.0/ja/model_doc/bit#transformers.BitConfig)) and inputs.
The [BitForImageClassification](/docs/transformers/v5.8.0/ja/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/v5.8.0/ja/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/v5.8.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ImageClassifierOutputWithNoAttention](/docs/transformers/v5.8.0/ja/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)``

A [ImageClassifierOutputWithNoAttention](/docs/transformers/v5.8.0/ja/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/v5.8.0/ja/model_doc/bit#transformers.BitConfig)) and inputs.