CODEWITHSUNDEEP
pythontensorflowtensorflow.jstensorflowjs-converter
Plotin
Plotin

Reputation: 63

Can I use a tensorflowjs model in Python?

I am not really a tensorflow expert. I have been using it with provided models and code, played around a bit and am trying to get better with it.

I got a hold of a model that I'd like to play around with in the form of a tensorflowjs model (?). It is in the form a model.json with some "shard1ofX" files. I also got some JS code to accompany it which I kind of understand, but I am not really a JS developer and also would like to use the model and code not on the net but in a standalone application.

The model gets loaded like that in the JS implementation:

tf.loadGraphModel(path_to_model_json)

Is it somehow possible to read said model in the Python tensorflow implementation to use it? Googling around I found a ton of information about converting a model TO tensorflowjs format, but not the other way around.

Help would be greatly appreciated!

Upvotes: 1

Views: 543

Answers (2)

Yashwardhan Deshmukh
Yashwardhan Deshmukh

Reputation: 1

You can use the tfjs-graph-converter library:

First you install it using pip:

pip install tfjs-graph-converter

Then you can use

from tfjs_graph_converter.api import load_graph_model, graph_to_function_v2

# Load and convert model
graph = load_graph_model('model_js/model.json')
model_function = graph_to_function_v2(graph)

# Convert inputs to tensors
x_tensor = tf.convert_to_tensor(np.expand_dims(input_npy, axis=0), dtype=tf.float32)
y_tensor = tf.convert_to_tensor(np.expand_dims(ground_truth_npy, axis=0), dtype=tf.float32)

# Get prediction and calculate loss
y_pred = model_function(x_tensor)[0]  # Get first tensor from list of outputs

PS: My inputs were long arrays of shape n,1, so I had to use np.expand_dims in my code. However, the core logic is still pretty much the same. Hope this helps, have a nice day! :D

Upvotes: 0

peytoncas
peytoncas

Reputation: 953

The tfjs-converter project supports going from Javascript to Python. I haven't tested this but it looks like these flags should get the job done.

tfjs_converter --input_format tfjs_layers_model \
    --output_format keras_saved_model \
    /tmp/tensorflowjs_model \
    /tmp/keras_model

https://github.com/tensorflow/tfjs/blob/master/tfjs-converter/README.md#format-conversion-support-tables

Upvotes: 2

Related Questions