Unable to convert vgg16 model .pb to IR error

[pholmes]

When I try to convert my .pb to IR, I am getting this error:

[ FRAMEWORK ERROR ]  Cannot load input model: TensorFlow cannot read the model file: "/Users/patraholmes/openvino_2020.3.341/deployment_tools/model_optimizer/saved_model.pb" is incorrect TensorFlow model file. 

The file should contain one of the following TensorFlow graphs:

1. frozen graph in text or binary format

2. inference graph for freezing with checkpoint (--input_checkpoint) in text or binary format

3. meta graph

Make sure that --input_model_is_text is provided for a model in text format. By default, a model is interpreted in binary format. Framework error details: Error parsing message. 

****EDIT****

I have installed Tensorflow 1.14, then trained and saved my model using Tensorflow 1.x. Now when trying to convert I get this:

[ ERROR ]  Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.load.tf.loader.TFLoader'>): Graph contains 0 node after executing protobuf2nx. It may happen due to problems with loaded model. It considered as error because resulting IR will be empty which is not usual

[Peh_Intel]

Hi pholmes,

Thanks for reaching out to us.

Please share the command given to Model Optimizer to convert your model to Intermediate Representation (IR).

If possible, please also share your trained model files for us to reproduce your issue.

On the other hand, I observed that you’re using OpenVINO™ 2020.3. Hence, I would strongly recommend you install the latest OpenVINO™ which is 2021.3 and have a try.

Regards,

Peh

[Peh_Intel]

Hi pholmes,

Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored. 

Regards,

Peh