IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Docs/fix convert tf crnn model document (#14531)

Browse Source 
* Fixed freezing tf1 pre-trained model issue due to mix use of tf1 and tf2 API
* Fix review comments
* Apply suggestions from code review
This commit is contained in:
Xiake Sun 2023-02-02 03:36:48 +08:00 committed by GitHub
parent 6ac1636191
commit 302e5497dd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_CRNN_From_Tensorflow.md
View File

@ -1,56 +1,52 @@
# Converting a TensorFlow CRNN Model {#openvino_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_CRNN_From_Tensorflow} # Converting a TensorFlow CRNN Model {#openvino_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_CRNN_From_Tensorflow}
This tutorial explains how to convert a CRNN model to Intermediate Representation (IR). This tutorial explains how to convert a CRNN model to OpenVINO™ Intermediate Representation (IR).
There are several public versions of TensorFlow CRNN model implementation available on GitHub. This tutorial explains how to convert the model from There are several public versions of TensorFlow CRNN model implementation available on GitHub. This tutorial explains how to convert the model from
the [CRNN Tensorflow](https://github.com/MaybeShewill-CV/CRNN_Tensorflow) repository to IR. the [CRNN Tensorflow](https://github.com/MaybeShewill-CV/CRNN_Tensorflow) repository to IR, and is validated with Python 3.7, TensorFlow 1.15.0, and protobuf 3.19.0.
If you have another implementation of CRNN model, it can be converted to OpenVINO IR in a similar way. You need to get inference graph and run Model Optimizer on it. If you have another implementation of CRNN model, it can be converted to OpenVINO IR in a similar way. You need to get inference graph and run Model Optimizer on it.
**To convert this model to the IR:** **To convert the model to IR:**
**Step 1.** Clone this GitHub repository and checkout the commit: **Step 1.** Clone this GitHub repository and check out the commit:
1. Clone repository: 1. Clone the repository:
```sh ```sh
git clone https://github.com/MaybeShewill-CV/CRNN_Tensorflow.git git clone https://github.com/MaybeShewill-CV/CRNN_Tensorflow.git
``` ```
2. Checkout necessary commit: 2. Go to the `CRNN_Tensorflow` directory of the cloned repository:
```sh
cd path/to/CRNN_Tensorflow
```
3. Check out the necessary commit:
```sh ```sh
git checkout 64f1f1867bffaacfeacc7a80eebf5834a5726122 git checkout 64f1f1867bffaacfeacc7a80eebf5834a5726122
``` ```
**Step 2.** Train the model, using framework or use the pretrained checkpoint provided in this repository. **Step 2.** Train the model using the framework or the pretrained checkpoint provided in this repository.
**Step 3.** Create an inference graph: **Step 3.** Create an inference graph:
1. Go to the `CRNN_Tensorflow` directory of the cloned repository: 1. Add the `CRNN_Tensorflow` folder to `PYTHONPATH`.
```sh * For Linux:
cd path/to/CRNN_Tensorflow
```
2. Add `CRNN_Tensorflow` folder to `PYTHONPATH`.
* For Linux OS:
```sh ```sh
export PYTHONPATH="${PYTHONPATH}:/path/to/CRNN_Tensorflow/" export PYTHONPATH="${PYTHONPATH}:/path/to/CRNN_Tensorflow/"
``` ```
* For Windows OS add `/path/to/CRNN_Tensorflow/` to the `PYTHONPATH` environment variable in settings. * For Windows, add `/path/to/CRNN_Tensorflow/` to the `PYTHONPATH` environment variable in settings.
3. Open the `tools/test_shadownet.py` script. After `saver.restore(sess=sess, save_path=weights_path)` line, add the following code: 2. Edit the `tools/demo_shadownet.py` script. After `saver.restore(sess=sess, save_path=weights_path)` line, add the following code:
```python ```python
import tensorflow as tf
from tensorflow.python.framework import graph_io from tensorflow.python.framework import graph_io
frozen = tf.compat.v1.graph_util.convert_variables_to_constants(sess, sess.graph_def, ['shadow/LSTMLayers/transpose_time_major']) frozen = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def, ['shadow/LSTMLayers/transpose_time_major'])
graph_io.write_graph(frozen, '.', 'frozen_graph.pb', as_text=False) graph_io.write_graph(frozen, '.', 'frozen_graph.pb', as_text=False)
``` ```
4. Run the demo with the following command: 3. Run the demo with the following command:
```sh ```sh
python tools/test_shadownet.py --image_path data/test_images/test_01.jpg --weights_path model/shadownet/shadownet_2017-10-17-11-47-46.ckpt-199999 python tools/demo_shadownet.py --image_path data/test_images/test_01.jpg --weights_path model/shadownet/shadownet_2017-10-17-11-47-46.ckpt-199999
``` ```
If you want to use your checkpoint, replace the path in the `--weights_path` parameter with a path to your checkpoint. If you want to use your checkpoint, replace the path in the `--weights_path` parameter with a path to your checkpoint.
5. In the `CRNN_Tensorflow` directory, you will find the inference CRNN graph `frozen_graph.pb`. You can use this graph with the OpenVINO™ toolkit 4. In the `CRNN_Tensorflow` directory, you will find the inference CRNN graph `frozen_graph.pb`. You can use this graph with OpenVINO
to convert the model into the IR and run inference. to convert the model to IR and then run inference.
**Step 4.** Convert the model into the IR: **Step 4.** Convert the model to IR:
```sh ```sh
mo --input_model path/to/your/CRNN_Tensorflow/frozen_graph.pb mo --input_model path/to/your/CRNN_Tensorflow/frozen_graph.pb
``` ```