Failed model_optimizer for SSD_300

川李000 · ‎05-07-2019

when I model_optimizer for SSD_300 I got error:

Shape [ 2 3 -1 256] is not fully defined for output 0 of "conv8_2/convolution". Use --input_shape with positive integers to override model input shapes.

(tensorflow-gpu) C:\Intel\computer_vision_sdk_2018.5.456\deployment_tools\model_optimizer>python mo_tf.py --input_model model.pb --input_shape "[2,300,300,3]"
Model Optimizer arguments:
Common parameters:
        - Path to the Input Model:      C:\Intel\computer_vision_sdk_2018.5.456\deployment_tools\model_optimizer\model.pb
        - Path for generated IR:        C:\Intel\computer_vision_sdk_2018.5.456\deployment_tools\model_optimizer\.
        - IR output name:       model
        - Log level:    ERROR
        - Batch:        Not specified, inherited from the model
        - Input layers:         Not specified, inherited from the model
        - Output layers:        Not specified, inherited from the model
        - Input shapes:         [2,300,300,3]
        - Mean values: Not specified
        - Scale values:         Not specified
        - Scale factor:         Not specified
        - Precision of IR:      FP32
        - Enable fusing:        True
        - Enable grouped convolutions fusing:   True
        - Move mean values to preprocess section:       False
        - Reverse input channels:       False
TensorFlow specific parameters:
        - Input model in text protobuf format: False
        - Offload unsupported operations:       False
        - Path to model dump for TensorBoard:   None
        - List of shared libraries with TensorFlow custom layers implementation:        None
        - Update the configuration file with input/output node names:   None
        - Use configuration file used to generate the model with Object Detection API: None
        - Operations to offload:        None
        - Patterns to offload: None
        - Use the config file: None
Model Optimizer version:        1.5.12.49d067a0
C:\Users\blowf\Anaconda3\envs\tensorflow-gpu\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
[ ERROR ] Shape [ 2   3 -1 256] is not fully defined for output 0 of "conv8_2/convolution". Use --input_shape with positive integers to override model input shapes.
[ ERROR ] Cannot infer shapes or values for node "conv8_2/convolution".
[ ERROR ] Not all output shapes were inferred or fully defined for node "conv8_2/convolution".
For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #40.
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function Convolution.infer at 0x0000022D6CC11378>.
[ 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 ] Stopped shape/value propagation at "conv8_2/convolution" node.
For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #38.

Sahira_Intel · ‎05-09-2019

Hi @李, 川

Is this the same error as you were getting here?

Best Regards,

Sahira

川李000 · ‎05-09-2019

hi Sahira：

Yes, I still have problems, please see this link https://software.intel.com/en-us/forums/computer-vision/topic/809260?language=en-us&https=1, thank you

Best Regards,

李川