Ekaterina Aidova
Ekaterina Aidova
Hi @joviyal-arun, could you provide more details about problem? Which device do you use for model loading? If it is possible, could you please provide full log of error and/or...
> Before running, install onnx_runtime via pip install onnxruntime or pip install onnxruntime-gpu (hasn't been tested yet) not sure regarding gpu support, but it is possibly better to add info...
> Add onnx_runtime to requirements Possibly, it can be done as extras to model api module
Hi @likholat, please make `develop` as target branch for your request, thanks
@raviarora1209 I do not think that it is possible in your described way (throw -r) because we do not know format in which your model provide the results and how...
@raviarora1209 Currently it is not supported, but we may consider this opportunity in the future. Do you have preference on specific format? I believe for coco format you can directly...
@duanyao model accuracy reference provided on internal testset, not COCO dataset. Unfortunatly, we can not share details about our private data
@APrigarina there are yamllint found issue, please resolve > 14:55:59 ./models/public/wav2vec2-base/accuracy-check.yml > 14:55:59 9:13 error wrong indentation: expected 21 but found 12 (indentation) > 14:55:59 19:13 error wrong indentation: expected...
openvino 2022.3 release introduced python 3.10 support, please try
docker was updated to use different way and the latest GPU driver, so I believe this issue should be solved by this PR https://github.com/openvinotoolkit/openvino_notebooks/pull/1875