# ConvNeXT

## Overview

ConvNeXT モデルは、[A ConvNet for the 2020s](https://huggingface.co/papers/2201.03545) で Zhuang Liu、Hanzi Mao、Chao-Yuan Wu、Christoph Feichtenhofer、Trevor Darrell、Saining Xie によって提案されました。
ConvNeXT は、ビジョン トランスフォーマーの設計からインスピレーションを得た純粋な畳み込みモデル (ConvNet) であり、ビジョン トランスフォーマーよりも優れたパフォーマンスを発揮すると主張しています。

論文の要約は次のとおりです。

*視覚認識の「狂騒の 20 年代」は、最先端の画像分類モデルとして ConvNet にすぐに取って代わられた Vision Transformers (ViT) の導入から始まりました。
一方、バニラ ViT は、オブジェクト検出やセマンティック セグメンテーションなどの一般的なコンピューター ビジョン タスクに適用すると困難に直面します。階層型トランスフォーマーです
(Swin Transformers など) は、いくつかの ConvNet の以前の機能を再導入し、Transformers を汎用ビジョン バックボーンとして実用的に可能にし、幅広い環境で顕著なパフォーマンスを実証しました。
さまざまな視覚タスク。ただし、このようなハイブリッド アプローチの有効性は、依然として、固有の誘導性ではなく、トランスフォーマーの本質的な優位性によるところが大きいと考えられています。
畳み込みのバイアス。この作業では、設計空間を再検討し、純粋な ConvNet が達成できる限界をテストします。標準 ResNet を設計に向けて徐々に「最新化」します。
ビジョン Transformer の概要を確認し、途中でパフォーマンスの違いに寄与するいくつかの重要なコンポーネントを発見します。この調査の結果は、純粋な ConvNet モデルのファミリーです。
ConvNextと呼ばれます。 ConvNeXts は完全に標準の ConvNet モジュールから構築されており、精度と拡張性の点で Transformers と有利に競合し、87.8% の ImageNet トップ 1 精度を達成しています。
標準 ConvNet のシンプルさと効率を維持しながら、COCO 検出と ADE20K セグメンテーションでは Swin Transformers よりも優れたパフォーマンスを発揮します。*

 ConvNeXT アーキテクチャ。 元の論文から抜粋。

このモデルは、[nielsr](https://huggingface.co/nielsr) によって提供されました。 TensorFlow バージョンのモデルは [ariG23498](https://github.com/ariG23498) によって提供されました。
[gante](https://github.com/gante)、および [sayakpaul](https://github.com/sayakpaul) (同等の貢献)。元のコードは [こちら](https://github.com/facebookresearch/ConvNeXt) にあります。

## Resources

ConvNeXT の使用を開始するのに役立つ公式 Hugging Face およびコミュニティ (🌎 で示される) リソースのリスト。

- [ConvNextForImageClassification](/docs/transformers/v5.3.0/ja/model_doc/convnext#transformers.ConvNextForImageClassification) 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。

## ConvNextConfig[[transformers.ConvNextConfig]]

#### transformers.ConvNextConfig[[transformers.ConvNextConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.3.0/src/transformers/models/convnext/configuration_convnext.py#L24)

This is the configuration class to store the configuration of a [ConvNextModel](/docs/transformers/v5.3.0/ja/model_doc/convnext#transformers.ConvNextModel). It is used to instantiate an
ConvNeXT 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 ConvNeXT
[facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) architecture.

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.3.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.3.0/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:
```python
>>> from transformers import ConvNextConfig, ConvNextModel

>>> # Initializing a ConvNext convnext-tiny-224 style configuration
>>> configuration = ConvNextConfig()

>>> # Initializing a model (with random weights) from the convnext-tiny-224 style configuration
>>> model = ConvNextModel(configuration)

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

**Parameters:**

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

patch_size (`int`, *optional*, defaults to 4) : Patch size to use in the patch embedding layer.

num_stages (`int`, *optional*, defaults to 4) : The number of stages in the model.

hidden_sizes (`list[int]`, *optional*, defaults to [96, 192, 384, 768]) : Dimensionality (hidden size) at each stage.

depths (`list[int]`, *optional*, defaults to [3, 3, 9, 3]) : Depth (number of blocks) for each stage.

hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`) : The non-linear activation function (function or string) in each block. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.

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.

layer_scale_init_value (`float`, *optional*, defaults to 1e-6) : The initial value for the layer scale.

drop_path_rate (`float`, *optional*, defaults to 0.0) : The drop rate for stochastic depth.

out_features (`list[str]`, *optional*) : If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute.

out_indices (`list[int]`, *optional*) : If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute.

## ConvNextImageProcessor[[transformers.ConvNextImageProcessor]]

#### transformers.ConvNextImageProcessor[[transformers.ConvNextImageProcessor]]

[Source](https://github.com/huggingface/transformers/blob/v5.3.0/src/transformers/models/convnext/image_processing_convnext.py#L61)

Constructs a ConvNeXT image processor.

preprocesstransformers.ConvNextImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.3.0/src/transformers/models/convnext/image_processing_convnext.py#L197[{"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": "do_resize", "val": ": bool | None = None"}, {"name": "size", "val": ": dict[str, int] | None = None"}, {"name": "crop_pct", "val": ": float | None = None"}, {"name": "resample", "val": ": PIL.Image.Resampling | None = None"}, {"name": "do_rescale", "val": ": bool | None = None"}, {"name": "rescale_factor", "val": ": float | None = None"}, {"name": "do_normalize", "val": ": bool | None = None"}, {"name": "image_mean", "val": ": float | list[float] | None = None"}, {"name": "image_std", "val": ": float | list[float] | None = None"}, {"name": "return_tensors", "val": ": str | transformers.utils.generic.TensorType | None = None"}, {"name": "data_format", "val": ": ChannelDimension = "}, {"name": "input_data_format", "val": ": str | transformers.image_utils.ChannelDimension | None = None"}]- **images** (`ImageInput`) --
  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`.
- **do_resize** (`bool`, *optional*, defaults to `self.do_resize`) --
  Whether to resize the image.
- **size** (`dict[str, int]`, *optional*, defaults to `self.size`) --
  Size of the output image after `resize` has been applied. If `size["shortest_edge"]` >= 384, the image
  is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the
  image will be matched to `int(size["shortest_edge"]/ crop_pct)`, after which the image is cropped to
  `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`.
- **crop_pct** (`float`, *optional*, defaults to `self.crop_pct`) --
  Percentage of the image to crop if size 0

Preprocess an image or batch of images.

**Parameters:**

do_resize (`bool`, *optional*, defaults to `True`) : Controls whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by `do_resize` in the `preprocess` method.

size (`dict[str, int]` *optional*, defaults to `{"shortest_edge" : 384}`): Resolution of the output image after `resize` is applied. If `size["shortest_edge"]` >= 384, the image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"]/crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. Can be overridden by `size` in the `preprocess` method.

crop_pct (`float` *optional*, defaults to 224 / 256) : Percentage of the image to crop. Only has an effect if `do_resize` is `True` and size  1` a classification loss is computed (Cross-Entropy).0[ImageClassifierOutputWithNoAttention](/docs/transformers/v5.3.0/ja/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)`A [ImageClassifierOutputWithNoAttention](/docs/transformers/v5.3.0/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 ([ConvNextConfig](/docs/transformers/v5.3.0/ja/model_doc/convnext#transformers.ConvNextConfig)) and inputs.
The [ConvNextForImageClassification](/docs/transformers/v5.3.0/ja/model_doc/convnext#transformers.ConvNextForImageClassification) 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, ConvNextForImageClassification
>>> import torch
>>> from datasets import load_dataset

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

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/convnext-tiny-224")
>>> model = ConvNextForImageClassification.from_pretrained("facebook/convnext-tiny-224")

>>> 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 ([ConvNextForImageClassification](/docs/transformers/v5.3.0/ja/model_doc/convnext#transformers.ConvNextForImageClassification)) : 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/v5.3.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ImageClassifierOutputWithNoAttention](/docs/transformers/v5.3.0/ja/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)``

A [ImageClassifierOutputWithNoAttention](/docs/transformers/v5.3.0/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 ([ConvNextConfig](/docs/transformers/v5.3.0/ja/model_doc/convnext#transformers.ConvNextConfig)) and inputs.