Ekaterina Aidova

Results 115 comments of Ekaterina Aidova

@zhuo-yoyowz could you please check, the issue still reproducible or not?

@zhuo-yoyowz could you please try to add --num_attempts 5 in omz_downloader parameters? This parameter responsible for retrying failed downloading

Thank you, probably, we need to include this fix to notebook

@sanbuphy regarding ph-2 support, unfortunatly, this model is not good in chatbot scenario as it is not fine-tuned for this case. We prepared separated demo, that allow you run it...

@ryanloney @paularamo thank you for review, could you please look one more time? I applied your comments

> @eaidova it looks like our suggested changes may have broken some of the code/markdown sections. Can you take a look: ![image](https://user-images.githubusercontent.com/15709723/201139297-92d10490-d7b6-489b-9bbb-b31ca54ffdfc.png) @ryanloney My understanding is correct, you confused that...

@ryanloney incorrect note should be fixed now, looks like there is some difference between markdown representation between github and jupyterlab

@HENNESSYxie if I correctly understand, does your model trained on a different dataset? there is a parameter inside detect function, when calling non_maximum_suppression, nc - it is responsible for a...

@Ai-econ for achieving accurate results model required preserving aspect ratio of input image, during accruacy validation model input was reshaped according provided preprocessing rules

@Ai-econ they provided in accuracy checker config preprocessing section. Image resized with preserving aspect ratio, where height size will be 368 and width resized according to these rules https://github.com/openvinotoolkit/open_model_zoo/blob/270dcb5d995b7b5f1db2c08c0db3283a78393e42/tools/accuracy_checker/openvino/tools/accuracy_checker/preprocessor/resize.py#L33 and...