problems with input tensor shape

[Dirk8]

Testing benchmark_app reults in error:

Traceback (most recent call last):
File "/home/topinc/myenv/lib/python3.11/site-packages/openvino/tools/benchmark/main.py", line 562, in main
duration_ms = f"{benchmark.first_infer(requests):.2f}"
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/topinc/myenv/lib/python3.11/site-packages/openvino/tools/benchmark/benchmark.py", line 86, in first_infer
requests.wait_all()
RuntimeError: Exception from src/inference/src/cpp/infer_request.cpp:245:
Exception from core/async_infer_queue.cpp:107:
Exception from src/plugins/intel_cpu/src/node.cpp:769:
[CPU] Reshape node with name 'detected_classes' Exception from src/plugins/intel_cpu/src/shape_inference/custom/reshape.cpp:62:
[cpu]reshape: the shape of input data (1.1.6) conflicts with the reshape pattern (1.256)

Any help to get this running would be appreciated.

Raspberry Pi OS:

PRETTY_NAME="Debian GNU/Linux 12 (bookworm)"
NAME="Debian GNU/Linux"
VERSION_ID="12"
VERSION="12 (bookworm)"
VERSION_CODENAME=bookworm
ID=debian

OpenVino version:

2025.0.0-17942-1f68be9f594-releases/2025/0

[Aznie_Intel]

Hi Dirk8,

Thanks for reaching out. The error indicates a mismatch between the actual input shape of a tensor and the reshape pattern expected by the model.

To verify the model's expected input shape, you can use the -shape parameter:

 benchmark_app -m your_model.xml -d CPU -shape

If there's a mismatch, try specifying the correct input shape manually like this:

 benchmark_app -m your_model.xml -d CPU -shape "[1,256]"

Please give this a try and let me know if the issue persists.

Regards,

Aznie

[Aznie_Intel]

Hi Dirk8,

This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.

Regards,

Aznie