The purpose of this library is to import TFJS graph models into Tensorflow. This allows you to use TensorFlow.js models with Python in case you don't have access to the original formats or the models have been created in TFJS.
I'm neither a Python developer, nor do I know TensorFlow or TensorFlow.js. I created this package solely because I ran into an issue when trying to convert a pretrained TensorFlow.js model into a different format. I didn't have access to the pretrained original TF model and didn't have the resources to train it myself. I soon learned that I'm not alone with this issue so I sat down and wrote this little library.
If you find any part of the code to be non-idiomatic or know of a simpler way to achieve certain things, feel free to let me know, since I'm a beginner in both Python and especially TensorFlow (used it for the very first time in this very project).
- tensorflow 2.1+
- tensorflowjs 1.5.2+
The converter has been tested with tensorflowjs v1.7.2 and tensorflow v2.1. The Python version used was Python 3.7.7.
pip install tfjs-graph-converter
After the installation, you can run the packaged tfjs_graph_converter
binary
for quick and easy model conversion.
Positional Argument | Description |
---|---|
input_path |
Path to the TFJS Graph Model directory containing the model.json |
output_path |
For output format "tf_saved_model", a SavedModel target directory. For output format "tf_frozen_model", a frozen model file. |
Option | Description |
---|---|
-h , --help |
Show help message and exit |
--output_format |
Use tf_frozen_model (the default) to save a Tensorflow frozen model. tf_saved_model exports to a Tensorflow SavedModel instead. |
--saved_model_tags |
Specifies the tags of the MetaGraphDef to save, in comma separated string format. Defaults to "serve". Applicable only if --output format is tf_saved_model |
-v , --version |
Shows the version of the converter and its dependencies. |
-s , --silent |
Suppresses any output besides error messages. |
Alternatively, you can create your own converter programs using the module's API. The API is required to accomplish more complicated tasks, like packaging multiple TensorFlow.js models into a single SavedModel.
To convert a TensorFlow.js graph model to a TensorFlow frozen model (i.e. the
most common use case?), just specify the directory containing the model.json
,
followed by the path and file name of the frozen model like so:
tfjs_graph_converter path/to/js/model path/to/frozen/model.pb
The package installs the module tfjs_graph_converter
, which contains all the
functionality used by the converter script.
You can leverage the API to either load TensorFlow.js graph models directly for
use with your TensorFlow program (e.g. for inference, fine-tuning, or extending),
or use the advanced functionality to combine several TFJS models into a single
SavedModel
.
The latter is only supported using the API (it's just a single function call,
though, so don't panic 😉)