Skip to contents

Instantiates the ConvNeXtXLarge architecture.


  model_name = "convnext_xlarge",
  include_top = TRUE,
  include_preprocessing = TRUE,
  weights = "imagenet",
  input_tensor = NULL,
  input_shape = NULL,
  pooling = NULL,
  classes = 1000L,
  classifier_activation = "softmax"



String, name for the model.


Whether to include the fully-connected layer at the top of the network. Defaults to TRUE.


Boolean, whether to include the preprocessing layer at the bottom of the network.


One of NULL (random initialization), "imagenet" (pre-training on ImageNet-1k), or the path to the weights file to be loaded. Defaults to "imagenet".


Optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.


Optional shape tuple, only to be specified if include_top is FALSE. It should have exactly 3 inputs channels.


Optional pooling mode for feature extraction when include_top is FALSE. Defaults to NULL.

  • NULL means that the output of the model will be the 4D tensor output of the last convolutional layer.

  • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.

  • max means that global max pooling will be applied.


Optional number of classes to classify images into, only to be specified if include_top is TRUE, and if no weights argument is specified. Defaults to 1000 (number of ImageNet classes).


A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=TRUE. Set classifier_activation=NULL to return the logits of the "top" layer. Defaults to "softmax". When loading pretrained weights, classifier_activation can only be NULL or "softmax".


A model instance.


For image classification use cases, see this page for detailed examples. For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The base, large, and xlarge models were first pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The pre-trained parameters of the models were assembled from the official repository. To get a sense of how these parameters were converted to Keras compatible parameters, please refer to this repository.


Each Keras Application expects a specific kind of input preprocessing. For ConvNeXt, preprocessing is included in the model using a Normalization layer. ConvNeXt models expect their inputs to be float or uint8 tensors of pixels with values in the [0-255] range.

When calling the summary() method after instantiating a ConvNeXt model, prefer setting the expand_nested argument summary() to TRUE to better investigate the instantiated model.