This tutorial explains how to convert a CRNN model to Intermediate Representation (IR).
On GitHub*, you can find several public versions of TensorFlow* CRNN model implementation. This tutorial explains how to convert the model from the https://github.com/MaybeShewill-CV/CRNN_Tensorflow repository to IR. If you have another implementation of CRNN model, you can convert it to IR in similar way: you need to get inference graph and run the Model Optimizer on it.
To convert this model to the IR:
Step 1. Clone this GitHub repository and checkout the commit:
2. Checkout necessary commit:
Step 2. Train the model using framework or use the pretrained checkpoint provided in this repository.
Step 3. Create an inference graph:
CRNN_Tensorflow
directory with the cloned repository: 2. Add `CRNN_Tensorflow` folder to `PYTHONPATH`. * For Linux\* OS:
* For Windows\* OS add `/path/to/CRNN_Tensorflow/` to the `PYTHONPATH` environment variable in settings. 3. Open the `tools/demo_shadownet.py` script. After `saver.restore(sess=sess, save_path=weights_path)` line, add the following code:
4. Run the demo with the following command:
If you want to use your checkpoint, replace the path in the --weights_path
parameter with a path to your checkpoint.
CRNN_Tensorflow
directory, you will find the inference CRNN graph frozen_graph.pb
. You can use this graph with the OpenVINO™ toolkit to convert the model into IR and run inference.Step 4. Convert the model into IR: