Vladimir Zlobin
Vladimir Zlobin
Sorry, my bad. It should have been [face-detection-0204](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/intel/face-detection-0204) ```py import numpy as np import openvino as ov import cv2 core = ov.runtime.ie_api.Core() detection_model_xml = r"C:/Users/vzlobin/.cache/omz/intel/face-detection-0204/FP16/face-detection-0204.xml" detection_model = core.read_model(model=detection_model_xml) detection_input_layer =...
`ppp.input().model().set_layout("NCHW");` doesn't modify your model. It sets the info for `ppp` about internal model layout so `ppp.input().tensor().set_shape(input_shape).set_element_type(input_type).set_layout(tensor_layout);` knows whether the transpose is required.
The first is the input layout. It's the layout you are going to follow while providing the input for inference. The second is the model layout. That's how the model...
It seems I'm not educated enough to understand the problem description. @Maxim-Doronin, can you take a look?
I can't reproduce the issue: ```sh python3 -m venv venv source ./venv/bin/activate python -m pip install -U pip python -m pip install openvino==2024.0.0 python -m pip install demos/common/python python -c...
`multi_camera_multi_target_tracking_demo` nor `FP32\instance-segmentation-security-0228.xml` don't contain any specifics to dGPU. This the problem of inference itself. I don't have dGPU to verify the issue still exists. Please try the latest OpenVINO....
Since the issue is either exists in GPU plugin or already resolved, I can transfer this issue without waiting for your reply
I haven't looked into it yet. We still use C++11. You may find this helpful https://github.com/openvinotoolkit/open_model_zoo/blob/2029eefe2e57a0fd984069db1a28e7d7585fcfcc/demos/common/cpp/utils/src/images_capture.cpp#L82
Please fix `build/intel64/Release/face_recognition_demo` tests. I will fix the rest
If your hypothesis turns out to be true >This then could be a cause of a dependency of a dependency causing a sporadic issue you should update numpy version only...