Convert SSD MobileNet V1error using OpenVINO

[lin__xiaobo]

My cmd is "python3 model-optimizer/mo.py --framework tf \ --output_dir . \ --input_model frozen_inference_graph_face.pb \ --tensorflow_object_detection_api_pipeline_config pipeline.config \ --tensorflow_use_custom_operations_config extensions/front/tf/ssd_v2_support.json \ --reverse_input_channels --keep_shape_ops --log_level=DEBUG ", error message is "[ ERROR ] Cannot infer shapes or values for node "BoxPredictor_1/Reshape_1". [ ERROR ] Number of elements in input [ 1 10 10 18] and output [1, 1536, 3] of reshape node BoxPredictor_1/Reshape_1 mismatch [ ERROR ] [ ERROR ] It can happen due to bug in custom shape infer function . at 0x7f6ccc2a89d8>. [ ERROR ] Or because the node inputs have incorrect values/shapes. [ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape). [ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information. [ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (): Stopped shape/value propagation at "BoxPredictor_1/Reshape_1" node. For more information please refer to Model Optimizer FAQ (/deployment_tools/documentation/docs/MO_FAQ.html), question #38.". How can fix it? If I use extensions/front/tf/ssd_support.json instead, error message is "[ ERROR ] Cannot infer shapes or values for node "BoxPredictor_0/ClassPredictor/BiasAdd/Reshape". [ ERROR ] Number of elements in input [ 1 19 19 9] and output [1, 35, 91] of reshape node BoxPredictor_0/ClassPredictor/BiasAdd/Reshape mismatch [ ERROR ] [ ERROR ] It can happen due to bug in custom shape infer function . at 0x7f158d907048>. [ ERROR ] Or because the node inputs have incorrect values/shapes. [ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape). [ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information. [ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (): Stopped shape/value propagation at "BoxPredictor_0/ClassPredictor/BiasAdd/Reshape" node. For more information please refer to Model Optimizer FAQ (/deployment_tools/documentation/docs/MO_FAQ.html), question #38.".

[Shubha_R_Intel]

Dear lin, xiaobo,

Is your SSD MobileNet V1 chosen from the supported and validated tensorflow model optimizer list ? If so, which model did you choose ? If chosen from this list, you should not have these errors.

Thanks,

Shubha