The tfhub package provides R wrappers to TensorFlow Hub.
TensorFlow Hub is a library for reusable machine learning modules.
TensorFlow Hub is a library for the publication, discovery, and consumption of reusable parts of machine learning models. A module is a self-contained piece of a TensorFlow graph, along with its weights and assets, that can be reused across different tasks in a process known as transfer learning. Transfer learning can:
You can install the released version of tfhub from CRAN with:
And the development version from GitHub with:
# install.packages("devtools") ::install_github("rstudio/tfhub")devtools
After installing the tfhub package you need to install the TensorFlow Hub python module:
Modules can be loaded from URL’s and local paths using
Module’s behave like functions and can be called with Tensors eg:
<- tf$random$uniform(shape = shape(1,224,224,3), minval = 0, maxval = 1) input <- module(input)output
The easiest way to get started with tfhub is using
layer_hub. A Keras layer that loads a TensorFlow Hub module and prepares it for using with your model.
library(tfhub) library(keras) <- layer_input(shape = c(32, 32, 3)) input <- input %>% output # we are using a pre-trained MobileNet model! layer_hub(handle = "https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/2") %>% layer_dense(units = 10, activation = "softmax") <- keras_model(input, output) model %>% model compile( loss = "sparse_categorical_crossentropy", optimizer = "adam", metrics = "accuracy" )
We can then fit our model in the CIFAR10 dataset:
<- dataset_cifar10() cifar $train$x <- tf$image$resize(cifar$train$x/255, size = shape(224,224)) cifar %>% model fit( x = cifar$train$x, y = cifar$train$y, validation_split = 0.2, batch_size = 128 )
tfhub can also be used with tfdatasets:
tfhub adds a
step_pretrained_text_embedding that can be used with the recipes package.
An example can be found here.
tfhub.dev is a gallery of pre-trained model ready to be used with TensorFlow Hub.