Interface to 'TensorFlow' Hub
'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 train a model with a smaller dataset,
improve generalization, and speed up training.
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:
- Train a model with a smaller dataset,
- Improve generalization, and
- Speed up training.
You can install the development version from GitHub with:
# install.packages("devtools") devtools::install_github("rstudio/tfhub")
After installing the tfhub package you need to install the TensorFlow Hub python module:
Go to the website for more information.
Functions in tfhub
|hub_sparse_text_embedding_column||Module to construct dense representations from sparse text features.|
|reexports||Objects exported from other packages|
|hub_image_embedding_column||Module to construct a dense 1-D representation from the pixels of images.|
|hub_text_embedding_column||Module to construct a dense representation from a text feature.|
|bake.step_pretrained_text_embedding||Bake method for step_pretrained_text_embedding|
|install_tfhub||Install TensorFlow Hub|
|prep.step_pretrained_text_embedding||Prep method for step_pretrained_text_embedding|
Vignettes of tfhub
Last month downloads
|License||Apache License 2.0|
|SystemRequirements||TensorFlow >= 2.0 (https://www.tensorflow.org/)|
|Config/reticulate||list( packages = list( list(package = "tensorflow", pip = TRUE), list(package = "tensorflow_hub", pip = TRUE) ) )|
|Packaged||2020-05-22 20:31:59 UTC; dfalbel|
|Date/Publication||2020-05-22 20:50:02 UTC|
Include our badge in your README