umitkacar / ear-segmentation-ai Goto Github PK

URL : https://github.com/tiangolo/typer

It allows to us show colorful and easier CLI management (If color not supported It will be no color mode as well)

Hi, Mr. Umitkacar,
I want use your pre-train model to do ear segmentation in my images dataset.
In my photo, there is no head or face, so your model could not segment the ear,
so I want to fine-tune your model use my images dataset,
but the loss could not converge, and the result is terrible.
I would like to ask for the source training code of your model.
Thank you very much.

Describe the bug
Hello,
There seems to be a tiny issue with the image mode. According to the sample code, I need to give the image file name while using the image mode:

python -m earsegmentationai.main picture-capture --folderpath "/path/filename.png" --device "cpu"

and this is safeguarded in the following code

However, in ear_segmentation_image the passed path is supposed to be a folder path that contains the picture(s)

To Reproduce

1. Run the example code of the image mode, provided in the README.MD
2. Image cannot be found

Hi,

I found your model is very helpful, can I ask for the dataset that you are using? Can this model be deployed into the mobile platform?

Thanks for your great work.