experiments
/
STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Recommend Netron for TF Lite model visualization 

PiperOrigin-RevId: 316750470
Change-Id: Id794ed7b2a8405cf5821fb106e8861d8aacef22f
This commit is contained in:
Khanh LeViet 2020-06-16 13:48:29 -07:00 committed by TensorFlower Gardener
parent 8cf2895fcc
commit 23910c191f
1 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
tensorflow/lite/g3doc/guide/faq.md
View File

@ -45,30 +45,37 @@ or file a [new one](https://github.com/tensorflow/tensorflow/issues).
#### How do I determine the inputs/outputs for GraphDef protocol buffer? #### How do I determine the inputs/outputs for GraphDef protocol buffer?
The easiest way to inspect a graph from a `.pb` file is to use the The easiest way to inspect a graph from a `.pb` file is to use
[Netron](https://github.com/lutzroeder/netron), an open-source viewer for
machine learning models.
If Netron cannot open the graph, you can try the
[summarize_graph](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tools/graph_transforms/README.md#inspecting-graphs) [summarize_graph](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tools/graph_transforms/README.md#inspecting-graphs)
tool. tool.
If that approach yields an error, you can visualize the GraphDef with If the summarize_graph tool yields an error, you can visualize the GraphDef with
[TensorBoard](https://www.tensorflow.org/guide/summaries_and_tensorboard) and [TensorBoard](https://www.tensorflow.org/guide/summaries_and_tensorboard) and
look for the inputs and outputs in the graph. To visualize a `.pb` file, use the look for the inputs and outputs in the graph. To visualize a `.pb` file, use the
[`import_pb_to_tensorboard.py`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/import_pb_to_tensorboard.py) [`import_pb_to_tensorboard.py`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/import_pb_to_tensorboard.py)
script like below: script like below:
```sh ```shell
python import_pb_to_tensorboard.py --model_dir <model path> --log_dir <log dir path> python import_pb_to_tensorboard.py --model_dir <model path> --log_dir <log dir path>
``` ```
#### How do I inspect a `.tflite` file? #### How do I inspect a `.tflite` file?
TensorFlow Lite models can be visualized using the [Netron](https://github.com/lutzroeder/netron) is the easiest way to visualize a
TensorFlow Lite model.
If Netron cannot open your TensorFlow Lite model, you can try the
[visualize.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tools/visualize.py) [visualize.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tools/visualize.py)
script in our repository. script in our repository.
* [Clone the TensorFlow repository](https://www.tensorflow.org/install/source) * [Clone the TensorFlow repository](https://www.tensorflow.org/install/source)
* Run the `visualize.py` script with bazel: * Run the `visualize.py` script with bazel:
```sh ```shell
bazel run //tensorflow/lite/tools:visualize model.tflite visualized_model.html bazel run //tensorflow/lite/tools:visualize model.tflite visualized_model.html
``` ```