Unable to Convert TensorFlow* (TF) Saved Model (.Pb) Format into Intermediate Representation (IR)

• Converted custom TensorFlow model with the commands below:

  mo --input_model saved_model.pb --input_shape [1,3,130,206] --reverse_input_channels

• Encountered error:

  [ FRAMEWORK ERROR ] Cannot load input model: TensorFlow cannot read the model file:

  "\openvino_notebooks\notebooks\101-tensorflow-to-openvino\model\roi_train_model\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

For conversion of the Saved Model model format, the directory should have these components:

1. A SavedModel Protocol Buffer
   • saved_model.pb/.pbtxt 
     • graph definitions as MetaGraphDef
2. Assets
   • Contains auxiliary files such as vocabularies
3. Extra Assets
   • Subfolder where higher-level libraries and users can add their own assets that coexist with the model but aren't loaded by the graph.
4. Variables
   • Includes outputs from Tensorflow Saver

Refer to Converting a TensorFlow Model.