- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I try to convert Mobilenet model was retrained with TF2 to OpenVino model.
I use the "SavedModel" loading for loading the TF model with this command:
"python mo.py --framework tf --saved_model_dir <Path to model>\model --model_name ir_1 --output_dir <Path to model>\Out"
and I get this error:
[ ERROR ] Unexpected exception happened during extracting attributes for node conv_pw_13_bn/moving_variance/Read/ReadVariableOp.
Original exception message: 'ascii' codec can't decode byte 0xca in position 1: ordinal not in range(128)
When I converted similar model with frozen graph loading and Tensorflow 1.13 everything was right.
Is known about a problem with Mobilenet layers that was trained with TF2?
- Tested with OpenVino 2019 R3.1 and 2019 R2
Thanks,
Eliav
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Eliav,
Thanks for reaching out. Currently the Model Optimizer does not support Tensorflow 2.0. However, there has been reports by other users that if you use Tensorflow 1.14 freeze_graph.py to freeze a Tensorflow 2.0 model the Model Optimizer may accept it.
Hope this helps.
Regards,
Jesus
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Eliav,
Thanks for reaching out. Currently the Model Optimizer does not support Tensorflow 2.0. However, there has been reports by other users that if you use Tensorflow 1.14 freeze_graph.py to freeze a Tensorflow 2.0 model the Model Optimizer may accept it.
Hope this helps.
Regards,
Jesus
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
This is not true at all! I have wasted another day based on the fact Intel staff have said that you can convert TF2 models by freezing them in TF1.14. It does not work.
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page