tf.keras.applications.InceptionV3( include_top=True, weights="imagenet", input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation="softmax", )
Instantiates the Inception v3 architecture.
This function returns a Keras image classification model, optionally loaded with weights pre-trained on ImageNet.
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.
Note: each Keras Application expects a specific kind of input preprocessing.
on your inputs before passing them to the model.
inception_v3.preprocess_input will scale input pixels between -1 and 1.
imagenet(pre-training on ImageNet), or the path to the weights file to be loaded. Default to
layers.Input()) to use as image input for the model.
input_tensoris useful for sharing inputs between multiple different networks. Default to None.
include_topis False (otherwise the input shape has to be
(299, 299, 3)(with
channels_lastdata format) or
(3, 299, 299)(with
channels_firstdata format). It should have exactly 3 inputs channels, and width and height should be no smaller than 75. E.g.
(150, 150, 3)would be one valid value.
input_shapewill be ignored if the
None(default) means that the output of the model will be the 4D tensor output of the last convolutional block.
avgmeans that global average pooling will be applied to the output of the last convolutional block, and thus the output of the model will be a 2D tensor.
maxmeans that global max pooling will be applied.
include_topis True, and if no
weightsargument is specified. Default to 1000.
stror callable. The activation function to use on the "top" layer. Ignored unless
classifier_activation=Noneto return the logits of the "top" layer. When loading pretrained weights,
classifier_activationcan only be