# ConvNeXt V2

## Overview

ConvNeXt V2 モデルは、Sanghyun Woo、Shobhik Debnath、Ronghang Hu、Xinlei Chen、Zhuang Liu, In So Kweon, Saining Xie. によって [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://huggingface.co/papers/2301.00808) で提案されました。
ConvNeXt V2 は、Vision Transformers 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、[ConvNeXT](convnext) の後継です。

論文の要約は次のとおりです。

*アーキテクチャの改善と表現学習フレームワークの改善により、視覚認識の分野は 2020 年代初頭に急速な近代化とパフォーマンスの向上を実現しました。たとえば、ConvNeXt に代表される最新の ConvNet は、さまざまなシナリオで強力なパフォーマンスを実証しています。これらのモデルはもともと ImageNet ラベルを使用した教師あり学習用に設計されましたが、マスク オートエンコーダー (MAE) などの自己教師あり学習手法からも潜在的に恩恵を受けることができます。ただし、これら 2 つのアプローチを単純に組み合わせると、パフォーマンスが標準以下になることがわかりました。この論文では、完全畳み込みマスク オートエンコーダ フレームワークと、チャネル間の機能競合を強化するために ConvNeXt アーキテクチャに追加できる新しい Global Response Normalization (GRN) 層を提案します。この自己教師あり学習手法とアーキテクチャの改善の共同設計により、ConvNeXt V2 と呼ばれる新しいモデル ファミリが誕生しました。これにより、ImageNet 分類、COCO 検出、ADE20K セグメンテーションなどのさまざまな認識ベンチマークにおける純粋な ConvNet のパフォーマンスが大幅に向上します。また、ImageNet でトップ 1 の精度 76.7% を誇る効率的な 370 万パラメータの Atto モデルから、最先端の 88.9% を達成する 650M Huge モデルまで、さまざまなサイズの事前トレーニング済み ConvNeXt V2 モデルも提供しています。公開トレーニング データのみを使用した精度*。

 ConvNeXt V2 アーキテクチャ。 元の論文から抜粋。

このモデルは [adirik](https://huggingface.co/adirik) によって提供されました。元のコードは [こちら](https://github.com/facebookresearch/ConvNeXt-V2) にあります。

## Resources

ConvNeXt V2 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。

- [ConvNextV2ForImageClassification](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2ForImageClassification) 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)。

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。

## ConvNextV2Config[[transformers.ConvNextV2Config]]

#### transformers.ConvNextV2Config[[transformers.ConvNextV2Config]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.0/src/transformers/models/convnextv2/configuration_convnextv2.py#L25)

This is the configuration class to store the configuration of a ConvNextV2Model. It is used to instantiate a Convnextv2
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 [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.6.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.6.0/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:
```python
>>> from transformers import ConvNeXTV2Config, ConvNextV2Model

>>> # Initializing a ConvNeXTV2 convnextv2-tiny-1k-224 style configuration
>>> configuration = ConvNeXTV2Config()

>>> # Initializing a model (with random weights) from the convnextv2-tiny-1k-224 style configuration
>>> model = ConvNextV2Model(configuration)

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

**Parameters:**

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

patch_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `4`) : The size (resolution) of each patch.

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

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

depths (`Union[list[int], tuple[int, ...]]`, *optional*, defaults to `(3, 3, 9, 3)`) : Depth of each layer in the Transformer.

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

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.

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

image_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `224`) : The size (resolution) of each image.

## ConvNextV2Model[[transformers.ConvNextV2Model]]

#### transformers.ConvNextV2Model[[transformers.ConvNextV2Model]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.0/src/transformers/models/convnextv2/modeling_convnextv2.py#L279)

The bare Convnextv2 Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.6.0/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.ConvNextV2Model.forwardhttps://github.com/huggingface/transformers/blob/v5.6.0/src/transformers/models/convnextv2/modeling_convnextv2.py#L293[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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
  [ConvNextImageProcessor](/docs/transformers/v5.6.0/ja/model_doc/convnext#transformers.ConvNextImageProcessor). See `ConvNextImageProcessor.__call__()` for details (`processor_class` uses
  [ConvNextImageProcessor](/docs/transformers/v5.6.0/ja/model_doc/convnext#transformers.ConvNextImageProcessor) for processing images).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 ([ConvNextV2Config](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2Config)) and inputs.
The [ConvNextV2Model](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2Model) 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 ([ConvNextV2Model](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2Model)) : 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/v5.6.0/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 ([ConvNextV2Config](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2Config)) and inputs.

## ConvNextV2ForImageClassification[[transformers.ConvNextV2ForImageClassification]]

#### transformers.ConvNextV2ForImageClassification[[transformers.ConvNextV2ForImageClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.6.0/src/transformers/models/convnextv2/modeling_convnextv2.py#L322)

ConvNextV2 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/v5.6.0/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.ConvNextV2ForImageClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.6.0/src/transformers/models/convnextv2/modeling_convnextv2.py#L340[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | 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
  [ConvNextImageProcessor](/docs/transformers/v5.6.0/ja/model_doc/convnext#transformers.ConvNextImageProcessor). See `ConvNextImageProcessor.__call__()` for details (`processor_class` uses
  [ConvNextImageProcessor](/docs/transformers/v5.6.0/ja/model_doc/convnext#transformers.ConvNextImageProcessor) 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).0[ImageClassifierOutputWithNoAttention](/docs/transformers/v5.6.0/ja/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)`A [ImageClassifierOutputWithNoAttention](/docs/transformers/v5.6.0/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 ([ConvNextV2Config](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2Config)) and inputs.
The [ConvNextV2ForImageClassification](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2ForImageClassification) 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, ConvNextV2ForImageClassification
>>> import torch
>>> from datasets import load_dataset

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

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/convnextv2-tiny-1k-224")
>>> model = ConvNextV2ForImageClassification.from_pretrained("facebook/convnextv2-tiny-1k-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 ([ConvNextV2ForImageClassification](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2ForImageClassification)) : 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/v5.6.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[ImageClassifierOutputWithNoAttention](/docs/transformers/v5.6.0/ja/main_classes/output#transformers.modeling_outputs.ImageClassifierOutputWithNoAttention) or `tuple(torch.FloatTensor)``

A [ImageClassifierOutputWithNoAttention](/docs/transformers/v5.6.0/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 ([ConvNextV2Config](/docs/transformers/v5.6.0/ja/model_doc/convnextv2#transformers.ConvNextV2Config)) and inputs.