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 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 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 によって提供されました。元のコードは こちら 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 は、この サンプル スクリプト および ノートブック。
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
class transformers.ConvNextV2Config
< source >( num_channels = 3 patch_size = 4 num_stages = 4 hidden_sizes = None depths = None hidden_act = 'gelu' initializer_range = 0.02 layer_norm_eps = 1e-12 drop_path_rate = 0.0 image_size = 224 out_features = None out_indices = None **kwargs )
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 (
strorfunction, 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. - 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 andout_indicesis set, will default to the corresponding stages. If unset andout_indicesis unset, will default to the last stage. Must be in the same order as defined in thestage_namesattribute. - 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 andout_featuresis set, will default to the corresponding stages. If unset andout_featuresis unset, will default to the last stage. Must be in the same order as defined in thestage_namesattribute.
This is the configuration class to store the configuration of a ConvNextV2Model. It is used to instantiate an 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 ConvNeXTV2 facebook/convnextv2-tiny-1k-224 architecture.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> 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.configConvNextV2Model
class transformers.ConvNextV2Model
< source >( config )
Parameters
- config (ConvNextV2Config) — 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() method to load the model weights.
The bare ConvNextV2 model outputting raw features without any specific head on top. This model is a PyTorch 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.
forward
< source >( pixel_values: FloatTensor = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.BaseModelOutputWithPoolingAndNoAttention or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using ConvNextImageProcessor. See ConvNextImageProcessor.call() for details. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutputWithPoolingAndNoAttention or tuple(torch.FloatTensor)
A transformers.modeling_outputs.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) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
torch.FloatTensorof shape(batch_size, hidden_size)) — Last layer hidden-state after a pooling operation on the spatial dimensions. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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.
The 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.
Example:
>>> from transformers import AutoImageProcessor, ConvNextV2Model
>>> 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 = ConvNextV2Model.from_pretrained("facebook/convnextv2-tiny-1k-224")
>>> inputs = image_processor(image, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 768, 7, 7]ConvNextV2ForImageClassification
class transformers.ConvNextV2ForImageClassification
< source >( config )
Parameters
- config (ConvNextV2Config) — 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() method to load the model weights.
ConvNextV2 Model with an image classification head on top (a linear layer on top of the pooled features), e.g. for ImageNet.
This model is a PyTorch 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.
forward
< source >( pixel_values: FloatTensor = None labels: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.modeling_outputs.ImageClassifierOutputWithNoAttention or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using ConvNextImageProcessor. See ConvNextImageProcessor.call() for details. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the image classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.ImageClassifierOutputWithNoAttention or tuple(torch.FloatTensor)
A 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) and inputs.
- loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. - logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). - hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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.
The 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.
Example:
>>> 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])
tabby, tabby catTFConvNextV2Model
class transformers.TFConvNextV2Model
< source >( config: ConvNextV2Config *inputs **kwargs )
Parameters
- config (ConvNextV2Config) — 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() method to load the model weights.
The bare ConvNextV2 model outputting raw features without any specific head on top. This model inherits from TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
TensorFlow models and layers in transformers accept two formats as input:
- having all inputs as keyword arguments (like PyTorch models), or
- having all inputs as a list, tuple or dict in the first positional argument.
The reason the second format is supported is that Keras methods prefer this format when passing inputs to models
and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just
pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second
format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with
the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first
positional argument:
- a single Tensor with
pixel_valuesonly and nothing else:model(pixel_values) - a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([pixel_values, attention_mask])ormodel([pixel_values, attention_mask, token_type_ids]) - a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({"pixel_values": pixel_values, "token_type_ids": token_type_ids})
Note that when creating models and layers with subclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!
call
< source >( pixel_values: TFModelInputType | None = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None training: bool = False ) → transformers.modeling_tf_outputs.TFBaseModelOutputWithPoolingAndNoAttention or tuple(tf.Tensor)
Parameters
- pixel_values (
np.ndarray,tf.Tensor,List[tf.Tensor],Dict[str, tf.Tensor]orDict[str, np.ndarray]and each example must have the shape(batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See ConvNextImageProcessor.call() for details. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set toTrue.
Returns
transformers.modeling_tf_outputs.TFBaseModelOutputWithPoolingAndNoAttention or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFBaseModelOutputWithPoolingAndNoAttention or a tuple of tf.Tensor (if
return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the
configuration (ConvNextV2Config) and inputs.
-
last_hidden_state (
tf.Tensorof shape(batch_size, num_channels, height, width)) — Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
tf.Tensorof shape(batch_size, hidden_size)) — Last layer hidden-state after a pooling operation on the spatial dimensions. -
hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(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.
The TFConvNextV2Model 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.
Example:
>>> from transformers import AutoImageProcessor, TFConvNextV2Model
>>> 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 = TFConvNextV2Model.from_pretrained("facebook/convnextv2-tiny-1k-224")
>>> inputs = image_processor(image, return_tensors="tf")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 768, 7, 7]TFConvNextV2ForImageClassification
class transformers.TFConvNextV2ForImageClassification
< source >( config: ConvNextV2Config *inputs **kwargs )
Parameters
- config (ConvNextV2Config) — 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() method to load the model weights.
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 TFPreTrainedModel. 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 tf.keras.Model subclass. Use it as a regular TF 2.0 Keras Model and refer to the TF 2.0 documentation for all matter related to general usage and behavior.
TensorFlow models and layers in transformers accept two formats as input:
- having all inputs as keyword arguments (like PyTorch models), or
- having all inputs as a list, tuple or dict in the first positional argument.
The reason the second format is supported is that Keras methods prefer this format when passing inputs to models
and layers. Because of this support, when using methods like model.fit() things should “just work” for you - just
pass your inputs and labels in any format that model.fit() supports! If, however, you want to use the second
format outside of Keras methods like fit() and predict(), such as when creating your own layers or models with
the Keras Functional API, there are three possibilities you can use to gather all the input Tensors in the first
positional argument:
- a single Tensor with
pixel_valuesonly and nothing else:model(pixel_values) - a list of varying length with one or several input Tensors IN THE ORDER given in the docstring:
model([pixel_values, attention_mask])ormodel([pixel_values, attention_mask, token_type_ids]) - a dictionary with one or several input Tensors associated to the input names given in the docstring:
model({"pixel_values": pixel_values, "token_type_ids": token_type_ids})
Note that when creating models and layers with subclassing then you don’t need to worry about any of this, as you can just pass inputs like you would to any other Python function!
call
< source >( pixel_values: TFModelInputType | None = None output_hidden_states: Optional[bool] = None return_dict: Optional[bool] = None labels: np.ndarray | tf.Tensor | None = None training: Optional[bool] = False ) → transformers.modeling_tf_outputs.TFImageClassifierOutputWithNoAttention or tuple(tf.Tensor)
Parameters
- pixel_values (
np.ndarray,tf.Tensor,List[tf.Tensor],Dict[str, tf.Tensor]orDict[str, np.ndarray]and each example must have the shape(batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See ConvNextImageProcessor.call() for details. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. This argument can be used only in eager mode, in graph mode the value in the config will be used instead. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. This argument can be used in eager mode, in graph mode the value will always be set toTrue. - labels (
tf.Tensorornp.ndarrayof shape(batch_size,), optional) — Labels for computing the image classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_tf_outputs.TFImageClassifierOutputWithNoAttention or tuple(tf.Tensor)
A transformers.modeling_tf_outputs.TFImageClassifierOutputWithNoAttention or a tuple of tf.Tensor (if
return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the
configuration (ConvNextV2Config) and inputs.
- loss (
tf.Tensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. - logits (
tf.Tensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). - hidden_states (
tuple(tf.Tensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftf.Tensor(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.
The TFConvNextV2ForImageClassification 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.
Example:
>>> from transformers import AutoImageProcessor, TFConvNextV2ForImageClassification
>>> import tensorflow as tf
>>> 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 = TFConvNextV2ForImageClassification.from_pretrained("facebook/convnextv2-tiny-1k-224")
>>> inputs = image_processor(image, return_tensors="tf")
>>> logits = model(**inputs).logits
>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = int(tf.math.argmax(logits, axis=-1))
>>> print(model.config.id2label[predicted_label])
tabby, tabby cat