In the last few days I have been systematically trying to run some customized model, like yolo with its own classes, on an OAK-D-Lite camera. I followed several tutorials provided by Luxonis, but none of them were successful. I can run the pre-trained models made available by the company, the camera is working OK. However, when trying my own model I can't. In all cases I fail in the last step. When executing the command: "python3 main.py --config yolov8strained.json", as described by the tutorial luxonis/depthai-ml-trainingblob/master/colab-notebooks/YoloV8_training.ipynb. I get the following message: config: yolov8strained.json
Downloading C:\Users\sandro.vilela\.cache\blobconverter\yolov8strained_openvino_2021.4_6shave.blob...
{
"exit_code": 1,
"message": "Command failed with exit code 1, command: /opt/intel/openvino2021_4/deployment_tools/inference_engine/lib/intel64/myriad_compile -m /tmp/blobconverter/49050601ac2d4968a2261f97af1294fa/yolov8strained/FP16/yolov8strained. xml -o /tmp /blobconverter/49050601ac2d4968a2261f97af1294fa/yolov8strained/FP16/yolov8strained.blob -c /tmp/blobconverter/49050601ac2d4968a2261f97af1294fa/myriad_compile_config.txt -ip U8",
"stderr": "Unknown model format! Cannot find reader for model format: xml and read the model: /tmp/blobconverter/49050601ac2d4968a2261f97af1294fa/yolov8strained/FP16/yolov8strained.xml. Please check that reader library exists in your PATH.\\n" ,
"stdout": "Inference Engine: \\n\\tIE version ......... 2021.4.2\\n\\tBuild ........... 2021.4.2-3974-e2a469a3450-releases/ 2021/4\\n"
}
Closing OAK camera
File "C:\Users\sandro.vilela\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\requests\models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: BAD REQUEST for url: https://blobconverter.luxonis.com/compile?version=2021.4&no_cache=False