I have the following issue: I'm trying to convert my OpenVINO model to a blob to use it with my OAK cameras, and I'm getting the following output:
Error Message:
Command failed with exit code 1, command: /app/venvs/venv2021_4/bin/python /app/model_compiler/openvino_2021.4/converter.py --precisions FP16 --output_dir /tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f --download_dir /tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f --name patentesv1 --model_root /tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f
Console output (stdout):
========== Converting patentesv1 to IR (FP16)
Conversion command: /app/venvs/venv2021_4/bin/python -m mo --framework=onnx --data_type=FP16 --output_dir=/tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f/patentesv1/FP16 --model_name=patentesv1 --data_type=FP16 '--mean_values=[127.5,127.5,127.5]' '--scale_values=[255,255,255]' --input_model=/tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f/patentesv1/FP16/patentesv1.onnx
Model Optimizer arguments:
Common parameters:
- Path to the Input Model: /tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f/patentesv1/FP16/patentesv1.onnx - Path for generated IR: /tmp/blobconverter/bfcddb9b17ed42a788bd02adc1784b3f/patentesv1/FP16 - IR output name: patentesv1 - 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: Not specified, inherited from the model - Mean values: [127.5,127.5,127.5] - Scale values: [255,255,255] - Scale factor: Not specified - Precision of IR: FP16 - Enable fusing: True - Enable grouped convolutions fusing: True - Move mean values to preprocess section: None - Reverse input channels: FalseONNX specific parameters:
[ WARNING ] Failed to import Inference Engine Python API in: PYTHONPATH
[ WARNING ] libpython3.6m.so.1.0: cannot open shared object file: No such file or directory
[ WARNING ] Failed to import Inference Engine Python API in: /opt/intel/openvino2021_4/python/python3.8
[ WARNING ] libpython3.6m.so.1.0: cannot open shared object file: No such file or directory
[ WARNING ] Could not find the Inference Engine Python API. At this moment, the Inference Engine dependency is not required, but will be required in future releases.
[ WARNING ] Consider building the Inference Engine Python API from sources or try to install OpenVINO (TM) Toolkit using "install_prerequisites.sh"
Model Optimizer version: 2021.4.2-3974-e2a469a3450-releases/2021/4
FAILED:
patentesv1
Error output (stderr):
[ ERROR ] Cannot infer shapes or values for node "/model.22/dfl/Reshape".
[ ERROR ] Number of elements in input [ 1 34 8400] and output [1, 4, 16, 8400] of reshape node /model.22/dfl/Reshape mismatch
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function Reshape.infer at 0x7f5c9d532790>.
[ 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" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "/model.22/dfl/Reshape" node.
For more information please refer to Model Optimizer FAQ, question #38. (https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html?question=38#question-38)
More context:
- I have the same model working with yolov5s.
- When I try to convert the file yolov8s.pt, I can do it without any problems.
- My current model, which is causing issues, is based on yolov8s.
- The tool I'm using is https://blobconverter.luxonis.com/.
- I've always used http://tools.luxonis.com/, but this time it's generating an error and not showing any information.
Any recommendations?
Thank you.
